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

    Neuronpedia

    INDEX
    Explanations

    magnitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hayat
    -0.06
    ら
    -0.06
     هنوز
    -0.06
    ячи
    -0.06
    ニア
    -0.06
    ChangedEventArgs
    -0.06
    _va
    -0.06
    Ra
    -0.06
    +v
    -0.06
    cháze
    -0.06
    POSITIVE LOGITS
     GRE
    0.07
    hoe
    0.06
     Natural
    0.06
    gold
    0.06
     infancy
    0.06
     disorders
    0.06
    .toJSONString
    0.06
    人类
    0.06
    .isdigit
    0.06
     natural
    0.06
    Act Density 0.038%

    No Known Activations