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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ip
    1.00
    ak
    0.88
    ter
    0.86
    el
    0.84
    il
    0.84
    ют
    0.84
    ∗</
    0.84
    os
    0.83
    ཀ
    0.83
    ជីវ
    0.81
    POSITIVE LOGITS
    場合は
    1.04
     а
    1.02
     dogged
    0.96
     Prés
    0.91
     दिलीप
    0.91
    ન
    0.87
    তে
    0.85
     وعلى
    0.85
     applause
    0.85
     বিরুদ্ধে
    0.84
    Act Density 0.093%

    No Known Activations