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

    Neuronpedia

    INDEX
    Explanations

    sexual

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ::::::::
    -0.07
     пу
    -0.07
    .invalidate
    -0.07
    怖
    -0.07
     فی
    -0.07
    dae
    -0.06
    _initialized
    -0.06
     próxima
    -0.06
    梁
    -0.06
    umbotron
    -0.06
    POSITIVE LOGITS
     surg
    0.07
     sponsors
    0.06
     lesbian
    0.06
    irs
    0.06
    yc
    0.06
     electric
    0.06
    $
    0.06
    ást
    0.06
    ection
    0.06
     Lect
    0.06
    Act Density 0.001%

    No Known Activations