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

    Neuronpedia

    INDEX
    Explanations

    explicit or graphic sexual acts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    明らか
    0.44
    explicit
    0.39
    OPES
    0.39
    autiful
    0.38
    olar
    0.38
    agel
    0.37
     CLEAR
    0.37
    OST
    0.37
    een
    0.36
    قيق
    0.36
    POSITIVE LOGITS
     त्यौहार
    0.42
     conduct
    0.41
     keç
    0.38
     ਵ
    0.38
     বা
    0.38
    ുക
    0.38
    Anomaly
    0.38
     hoặc
    0.38
     plaid
    0.37
     paquetes
    0.36
    Act Density 0.009%

    No Known Activations