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

    Neuronpedia

    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    忘
    -0.07
    平坦
    -0.07
     radiant
    -0.07
    中山
    -0.07
     considerable
    -0.07
    当然是
    -0.06
     cash
    -0.06
    转化
    -0.06
    cheng
    -0.06
    器件
    -0.06
    POSITIVE LOGITS
     Movies
    0.07
    _lex
    0.07
    _BP
    0.06
    ну
    0.06
    かれ
    0.06
    ;/*
    0.06
     Bern
    0.06
    .employee
    0.06
     Fecha
    0.06
    ∗
    0.06
    Act Density 0.372%

    No Known Activations