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

    Neuronpedia

    INDEX
    Explanations

    proving the transgender

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     LB
    0.39
     Cellulose
    0.39
     ويب
    0.39
     vulture
    0.38
     Ν
    0.38
    Lith
    0.37
     sav
    0.36
     Telecom
    0.36
     choking
    0.35
     चाहेंगे
    0.35
    POSITIVE LOGITS
     bagaimana
    0.46
    كيف
    0.44
    自体
    0.43
     eigent
    0.42
    実際の
    0.42
     quels
    0.41
    }=$
    0.40
    ể
    0.40
     zichzelf
    0.39
    ەر
    0.39
    Act Density 0.000%

    No Known Activations