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

    Neuronpedia

    INDEX
    Explanations

    code keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Copy
    -0.08
    Ratio
    -0.07
    ,data
    -0.06
    .Download
    -0.06
    ٪
    -0.06
    (payload
    -0.06
    _Reg
    -0.06
    宜
    -0.06
    원을
    -0.06
     캐
    -0.06
    POSITIVE LOGITS
    ریز
    0.06
     может
    0.06
     най
    0.06
    禁止
    0.06
    GTK
    0.06
     █████
    0.06
     metallic
    0.06
     Tại
    0.06
    bur
    0.06
    uploaded
    0.05
    Act Density 0.030%

    No Known Activations