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

    Neuronpedia

    INDEX
    Explanations

    give you information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     цвет
    1.37
    ウィンドウ
    1.32
     цвето
    1.30
    lceil
    1.23
    アルバム
    1.22
     दिस
    1.22
     строки
    1.21
    白的
    1.20
    千年
    1.15
    グレード
    1.14
    POSITIVE LOGITS
     torque
    2.01
     force
    2.00
     kuvvet
    1.86
     exerted
    1.83
    force
    1.80
    torque
    1.76
     pressure
    1.71
    Shock
    1.69
    Force
    1.65
    Pressure
    1.64
    Act Density 0.641%

    No Known Activations