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

    Neuronpedia

    INDEX
    Explanations

    sexually suggestive content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Athen
    -0.07
     selbst
    -0.07
     rhs
    -0.07
     bis
    -0.06
     hen
    -0.06
     Paint
    -0.06
     مه
    -0.06
    086
    -0.06
    коп
    -0.06
    217
    -0.06
    POSITIVE LOGITS
    -Bar
    0.07
     мають
    0.06
     endorsements
    0.06
    ổng
    0.06
     vex
    0.06
    olec
    0.06
    .used
    0.06
     exposures
    0.06
     Recently
    0.06
    оряд
    0.06
    Act Density 0.090%

    No Known Activations