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

    Neuronpedia

    INDEX
    Explanations

    property acts and controls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    痍
    0.77
     ઉત્પાદ
    0.77
     พบ
    0.74
     favorables
    0.73
    避け
    0.71
    ቢያ
    0.71
    พาะ
    0.71
    éhez
    0.70
    支払い
    0.69
     vermeiden
    0.68
    POSITIVE LOGITS
     acts
    3.51
     act
    3.39
     serve
    3.14
     acted
    3.13
     acting
    3.07
     serves
    3.07
     Acts
    2.97
    acts
    2.79
    Acts
    2.78
    act
    2.68
    Act Density 1.594%

    No Known Activations