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

    Neuronpedia

    INDEX
    Explanations

    size and dimensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     injustices
    0.55
     wrongdoing
    0.53
     salaried
    0.49
     sanciones
    0.46
     abogado
    0.45
     disillusioned
    0.45
     Demokrat
    0.44
     coercive
    0.44
     financiero
    0.43
     vittime
    0.43
    POSITIVE LOGITS
     diameter
    1.12
    尺寸
    1.11
     width
    1.09
     dimensions
    1.06
     размеры
    1.04
     size
    1.03
    Dimensions
    1.03
    直径
    1.03
     размер
    0.99
    diameter
    0.97
    Act Density 0.165%

    No Known Activations