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

    Neuronpedia

    INDEX
    Explanations

    code or calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skirts
    -0.07
    :::::::::::::
    -0.06
    化学
    -0.06
     transistor
    -0.06
     лицо
    -0.06
     они
    -0.06
    <m
    -0.06
     magazines
    -0.06
    َال
    -0.06
    哭
    -0.06
    POSITIVE LOGITS
    ourcing
    0.07
    -help
    0.06
    勇
    0.06
    940
    0.06
    งค
    0.06
     Erotik
    0.06
     kia
    0.06
    _PRIV
    0.06
    veyor
    0.06
     User
    0.06
    Act Density 0.426%

    No Known Activations