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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .directive
    -0.07
    .GetCurrent
    -0.07
    .Undef
    -0.07
    没关系
    -0.06
    くなって
    -0.06
    ForegroundColor
    -0.06
     nieruchomości
    -0.06
    ᠦ
    -0.06
    .rightBarButtonItem
    -0.06
    .cum
    -0.06
    POSITIVE LOGITS
    生存
    0.08
     Filtering
    0.08
     ThreadPool
    0.08
     hostile
    0.08
    Mirror
    0.08
     feminine
    0.07
     anti
    0.07
     electoral
    0.07
    Под
    0.07
     valida
    0.07
    Act Density 0.204%

    No Known Activations