would place-like representations emerge in memory neurons for activation functions other than softmax?

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Transformer memory neurons resemble hippocampal place cells due to sparse softmax activation producing spatial tuningclaim0.795
  Interpretation of why memory neurons in the biologically-instantiated transformer architecture acquire place-cell-like properties.
• Softmax Activation Function as Neuronal Modelmethod0.786
  Using softmax to translate membrane potentials into firing rates, implementing lateral inhibition.
• Winner take-all architectures of decision-making are already commonplace in computational neuroscience, and the softmax function provides a smooth approximation.claim0.779
  Neural plausibility argument for softmax policy selection.
• Neural Representations of Location Composed of Spatially Periodic Bands (Krupic et al., 2012)concept0.778
  Discovery of band cells; TEM-t also recapitulates these representations.
• Novel place cell metric (largest connected component firing mass ratio) successfully distinguishes TEM-t memory neurons (place cells) from RNN neurons (grid cells)finding0.769
  Methodological validation result confirming the place-cell metric separates cell types in TEM-t.
• Linear representation hypothesis: neural networks represent meaningful concepts as directions in their activation spaces.hypothesis0.769
  Foundation for interpreting features as linear directions.
• Emergence of grid-like representations by training recurrent neural networks to perform spatial localization (Cueva & Wei, 2018)concept0.766
  RNN model recapitulating grid cells; related work category 4.
• Feature Neurons and Memory Neurons Architectureframework0.765
  Biologically plausible two-pool architecture from Krotov & Hopfield (2020) splitting self-attention into feature and memory neuron populations; used to interpret TEM-t place cells.