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

    Neuronpedia

    INDEX
    Explanations

    pad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .con
    -0.07
    Trou
    -0.07
    %%%%%%%%
    -0.06
     Boca
    -0.06
    학과
    -0.06
     OG
    -0.06
    _CTL
    -0.06
     Refriger
    -0.06
    "G
    -0.06
     KING
    -0.06
    POSITIVE LOGITS
    leşme
    0.07
     pinch
    0.07
    -fill
    0.07
    日本
    0.06
    /student
    0.06
     onPressed
    0.06
     activation
    0.06
    arto
    0.06
     plugged
    0.06
     porn
    0.06
    Act Density 0.003%

    No Known Activations