Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    math limits and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cortical
    -0.09
     genomes
    -0.09
     walls
    -0.08
    Walls
    -0.08
     grids
    -0.08
    Editable
    -0.07
    Actors
    -0.07
    -mêmes
    -0.07
     galaxies
    -0.07
    Naming
    -0.07
    POSITIVE LOGITS
    趋
    0.13
     Alpine
    0.09
     famba
    0.08
    zeka
    0.08
     --->
    0.08
     მას
    0.08
     seng
    0.08
     squeeze
    0.08
     Apa
    0.08
    initializer
    0.08
    Act Density 0.016%

    No Known Activations