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

    Neuronpedia

    INDEX
    Explanations

    sexual acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    用於
    0.78
     rencontrer
    0.75
    стал
    0.74
     keyed
    0.74
     ouvrir
    0.72
     lactation
    0.71
     abrir
    0.71
    ี่ป
    0.70
    ড়ান্ত
    0.70
     किए
    0.70
    POSITIVE LOGITS
    fords
    0.85
    ur
    0.82
    i
    0.80
    m
    0.77
    dur
    0.75
     chu
    0.74
    e
    0.72
    a
    0.72
    o
    0.72
    mend
    0.69
    Act Density 0.002%

    No Known Activations