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

    Neuronpedia

    INDEX
    Explanations

    td

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Of
    -0.07
    صحاب
    -0.07
    _WINDOW
    -0.07
    的
    -0.07
     of
    -0.06
     individually
    -0.06
    无数次
    -0.06
    ение
    -0.06
     redistribute
    -0.06
    itate
    -0.06
    POSITIVE LOGITS
    świadc
    0.07
    (dec
    0.07
    _attached
    0.07
    Ordered
    0.07
    око
    0.07
     interven
    0.06
    определен
    0.06
     объявл
    0.06
     Selling
    0.06
    แฮ
    0.06
    Act Density 0.008%

    No Known Activations