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

    Neuronpedia

    INDEX
    Explanations

    code/data entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empres
    -0.07
     últ
    -0.06
     док
    -0.06
     повер
    -0.06
    司
    -0.06
    445
    -0.06
    ADIUS
    -0.06
    ,line
    -0.06
     skup
    -0.05
     ارز
    -0.05
    POSITIVE LOGITS
    UNET
    0.07
    _less
    0.07
    onDelete
    0.07
     userModel
    0.06
    _keyboard
    0.06
    鳥
    0.06
     ulong
    0.06
     ----------↵
    0.06
    .Ph
    0.06
    _preference
    0.06
    Act Density 0.003%

    No Known Activations