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

    Neuronpedia

    INDEX
    Explanations

    company suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人类
    -0.07
     Ό
    -0.06
    ества
    -0.06
    OfWork
    -0.06
    .savefig
    -0.06
    FlatButton
    -0.06
    .pc
    -0.06
     preferences
    -0.06
     srd
    -0.06
     управления
    -0.06
    POSITIVE LOGITS
    植
    0.08
    まと
    0.07
     напрям
    0.06
    .RED
    0.06
     specializes
    0.06
    phanumeric
    0.06
    :end
    0.06
     realise
    0.06
     spoiler
    0.06
     flames
    0.06
    Act Density 0.014%

    No Known Activations