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

    Neuronpedia

    INDEX
    Explanations

    women's rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    2.14
    ات
    1.76
    ра
    1.59
    いる
    1.57
    ać
    1.45
    sion
    1.44
    ামুটি
    1.43
    지에
    1.40
    지와
    1.40
    기
    1.39
    POSITIVE LOGITS
    ка
    1.79
     peroxide
    1.65
    и
    1.56
     hãy
    1.47
     विधवा
    1.44
    \%
    1.44
     versi
    1.44
     Forgot
    1.42
    áticas
    1.41
    ські
    1.41
    Act Density 0.002%

    No Known Activations