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

    Neuronpedia

    INDEX
    Explanations

    math and unsolved problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    協助
    -0.07
    Chuck
    -0.07
     une
    -0.07
     unlikely
    -0.06
    更何况
    -0.06
    _UD
    -0.06
     düşün
    -0.06
    心裡
    -0.06
     götür
    -0.06
     się
    -0.06
    POSITIVE LOGITS
    .Absolute
    0.07
     площ
    0.07
    _relu
    0.07
    .getTotal
    0.07
    闭环
    0.06
    中华人民
    0.06
     Scho
    0.06
    מסל
    0.06
    싲
    0.06
    INTEGER
    0.06
    Act Density 0.021%

    No Known Activations