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

    Neuronpedia

    INDEX
    Explanations

    : -

    np_max-act · gemini-2.0-flash

    This neuron selectively responds to floating‐point number tokens (decimal numeric literals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ylinder
    -0.07
     Door
    -0.07
    RH
    -0.07
     Wash
    -0.07
    strap
    -0.06
    Reverse
    -0.06
    wei
    -0.06
    الق
    -0.06
     lip
    -0.06
     wash
    -0.06
    POSITIVE LOGITS
    #####↵
    0.07
     texto
    0.07
    ATEST
    0.06
     berk
    0.06
    .${
    0.06
    ért
    0.06
     seper
    0.06
    官
    0.06
     لت
    0.06
     Δια
    0.06
    Act Density 0.039%

    No Known Activations