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

    Neuronpedia

    INDEX
    Explanations

    pornography and addiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.42
    مان
    0.39
    ณะ
    0.37
    መሳሳይ
    0.37
    مه
    0.36
    。
    0.35
    datatype
    0.34
    shop
    0.34
    idence
    0.33
    ERP
    0.33
    POSITIVE LOGITS
     использованием
    0.41
     arbres
    0.39
    ваны
    0.39
    ക്കുറ
    0.39
    ᱔
    0.38
     delantero
    0.38
     empleados
    0.38
    if
    0.38
    itação
    0.38
    '
    0.37
    Act Density 0.014%

    No Known Activations