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

    Neuronpedia

    INDEX
    Explanations

    sexual encounters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,str
    -0.07
    (idx
    -0.07
     MHz
    -0.07
    _IDS
    -0.07
    ยาย
    -0.07
    咋
    -0.06
     технологии
    -0.06
    isses
    -0.06
     Pinterest
    -0.06
    伸手
    -0.06
    POSITIVE LOGITS
    egral
    0.08
     окру
    0.07
     Class
    0.07
     결
    0.07
     measure
    0.07
    ساس
    0.06
    ouple
    0.06
    奂
    0.06
     ра�
    0.06
    Compact
    0.06
    Act Density 0.017%

    No Known Activations