Dynamic transitions between neural states are associated with flexible task-switching during a memory task

Flexible behavior requires switching between different task conditions. It is known that such task- switching is associated with costs in terms of slowed reaction time, reduced accuracy, or both. The neural correlates of task-switching have usually been studied by requiring participants to switch between distinct task demands that recruit different brain networks. Here, we investigated the transition of neural states underlying switching between two opposite memory-related processes (i.e., memory retrieval and memory suppression ) in a memory task. We investigated 26 healthy participants who performed a Think/No-Think task while being in the fMRI scanner. Behaviorally, we show that it was more difficult for participants to suppress unwanted memories when a No-Think was preceded by a Think trial instead of another No- Think trial. Neurally, we demonstrate that Think-to-No-Think switches were associated with an increase in control-related and a decrease in memory-related brain activity. Neural representations of task demand, assessed by decoding accuracy, were lower immediately after task switching compared to the non-switch transitions, suggesting a switch-induced delay in the neural transition towards the required task condition. This suggestion is corroborated by an association between condition-specific representational strength and condition-specific performance in switch trials. Taken together, we provided neural evidence from the time-resolved decoding approach to support the notion that carry-over of the previous task-set activation is associated with the switching cost leading to less successful memory suppression. Significance statement Our brain can switch between multiple tasks but at the cost of less optimal performance during transition. One possible neuroscientific explanation is that the representation of the task condition is not easy to be updated immediately after switching. Thus, weak representations for the task at hand explain performance costs. To test this, we applied brain decoding approaches to human fMRI data when participants switched between successive trials of memory retrieval and suppression. We found that switching leads to a weaker representation of the current task. The remaining representation of the previous, opposite task is associated with inferior performance in the current task. Therefore, timely updating of task representations is critical for task switching in the service of flexible behaviors.