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

    Neuronpedia

    INDEX
    Explanations

    Environmental impact reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shir
    -0.07
     옥
    -0.06
     Lynn
    -0.06
     Godzilla
    -0.06
    ında
    -0.06
     Фед
    -0.06
    ে
    -0.06
     Chanel
    -0.06
     Maid
    -0.06
    ╗
    -0.06
    POSITIVE LOGITS
     drug
    0.07
     Drug
    0.07
     Buffer
    0.06
     threat
    0.06
    (Expression
    0.06
     Natural
    0.06
     FLAGS
    0.06
    essian
    0.06
    _NATIVE
    0.06
     fot
    0.06
    Act Density 0.016%

    No Known Activations