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

    Neuronpedia

    INDEX
    Explanations

    importance and meaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Анг
    -0.07
    Statistic
    -0.06
    役
    -0.06
    ائ
    -0.06
    ниці
    -0.06
    ��
    -0.06
    家庭
    -0.06
     capt
    -0.06
    ayload
    -0.06
     化
    -0.06
    POSITIVE LOGITS
     kteří
    0.08
     dönüş
    0.07
    (box
    0.06
    ',"
    0.06
    _mas
    0.06
    izon
    0.06
     sonic
    0.06
     chlorine
    0.06
     Pistons
    0.06
     seized
    0.06
    Act Density 0.105%

    No Known Activations