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

    Neuronpedia

    INDEX
    Explanations

    Sensitivity/robustness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     expressions
    -0.08
     मेल
    -0.08
     رابط
    -0.07
     volle
    -0.07
    -то
    -0.07
     Russian
    -0.07
    LONG
    -0.07
    不上
    -0.07
    -0.07
    _Link
    -0.07
    POSITIVE LOGITS
     análisis
    0.08
     methodological
    0.08
    alternate
    0.08
    arte
    0.08
     robustness
    0.08
     analyses
    0.08
    analysis
    0.08
    alternative
    0.08
     sensitivity
    0.08
     gevo
    0.08
    Act Density 0.004%
    No Known Activations