Towards a Neural Foundation Model: A Probabilistic Spike Representation Model to Mitigate Neural Variability.

Spike train data encapsulate precise information about neuronal firing patterns and serve as the primary modality for modeling neural dynamics. However, the variability of spike data impairs model ability to generalize across sessions and subjects. To address this gap, spike representation models are designed to extract unified neural manifolds from large-scale recordings. While recent attention-based models have demonstrated feasibility, they are constrained by deterministic architectures that are incapable of capturing the intrinsic stochasticity of neural activity and electrode-induced misalignment. To overcome these limitations, we propose the Probabilistic Neural Representation Transformer (PNRT), a framework that models variable spike activities into a consistent latent probabilistic distribution. It also implements an activity-based neuronal reordering method that decouples the model from physical electrode positions to mitigate misalignment. Validated on three cross-subject datasets, PNRT outperforms deterministic baselines in both neural consistency modeling and behavior decoding, demonstrating its capability to model unified neural representation and robustness across spike variability.