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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dead
    -0.06
    nings
    -0.06
     gays
    -0.06
    Sex
    -0.06
    ema
    -0.06
    	V
    -0.06
    RB
    -0.06
    던
    -0.06
     neby
    -0.06
    贵
    -0.06
    POSITIVE LOGITS
    635
    0.07
    52
    0.07
     kutje
    0.06
    -that
    0.06
     wyst
    0.06
    73
    0.06
    Щ
    0.06
    recommended
    0.06
    essian
    0.06
     CultureInfo
    0.06
    Act Density 1.396%

    No Known Activations