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

    Neuronpedia

    INDEX
    Explanations

    your/my user data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aproxim
    -0.07
     mating
    -0.07
    _Ph
    -0.07
    恶
    -0.06
    _lon
    -0.06
    Girls
    -0.06
    €™
    -0.06
    Amb
    -0.06
    uct
    -0.06
    腦
    -0.06
    POSITIVE LOGITS
     Improve
    0.07
    :]:↵
    0.07
    AccessException
    0.07
    青年
    0.06
    (styles
    0.06
    (nameof
    0.06
     Asian
    0.06
    )animated
    0.06
    usion
    0.06
     Reader
    0.06
    Act Density 0.011%

    No Known Activations