(5/5) These results demonstrate that explicitly modeling the low-dimensional recurrent mechanisms underlying task execution is critical for identifying low-dimensional behaviorally relevant representations.

(4/5) A latent circuit model of PFC responses similarly reveals low-dimensional projections of neural activity in which irrelevant stimuli are suppressed. Larger representations of irrelevant stimuli on error trials further confirms the behavioral relevance of the inferred latent circuit.

(3/5) The orthonormal embedding allows validating the latent circuit mechanism via low-dimensional projections of activity and low-rank perturbations of connectivity. In contrast to previous studies, we find representations of stimuli are suppressed when they are irrelevant.

(2/5) To discover these latent mechanisms from high-dimensional responses, we developed the latent circuit model which simultaneously learns a low-dimensional recurrent neural network and an orthonormal embedding to jointly explain heterogeneous neural responses.

(1/5) Excited to share my work with @engeltatiana.bsky.social , out now in Nat Neuro! We show that RNNs use low-d latent circuit mechanisms for cognitive tasks. We find that context-dependent decisions in both RNNs and PFC arise from latent inhibitory mechanisms. www.nature.com/articles/s41...