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

    Neuronpedia

    INDEX
    Explanations

    cultural touchstone and sexual roleplay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    os
    0.96
    en
    0.93
    ens
    0.80
    س
    0.79
    em
    0.78
    ai
    0.78
    us
    0.77
    та
    0.75
    im
    0.73
    st
    0.72
    POSITIVE LOGITS
    ️⃣
    0.70
    Ι
    0.55
     {
    0.54
     예
    0.54
    ย์
    0.53
    เวล
    0.53
    І
    0.53
    O
    0.52
     선보
    0.52
    യ്യ
    0.52
    Act Density 0.651%

    No Known Activations