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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pony
    -0.06
     Succ
    -0.06
    uers
    -0.06
    _tC
    -0.06
    geries
    -0.06
    寒
    -0.06
    (Get
    -0.06
    Portrait
    -0.06
     grants
    -0.06
    ANJI
    -0.06
    POSITIVE LOGITS
     ویژگی
    0.08
    /**↵↵
    0.07
     checkBox
    0.07
    eldon
    0.07
    Comm
    0.06
     compuls
    0.06
     Finals
    0.06
     существ
    0.06
     blí
    0.06
    oola
    0.06
    Act Density 0.000%

    No Known Activations