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

    Neuronpedia

    INDEX
    Explanations

    code and specialized language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bolton
    -0.08
    amins
    -0.07
     Chuck
    -0.07
     Animated
    -0.07
     penned
    -0.06
     Almost
    -0.06
     threaded
    -0.06
     الأس
    -0.06
    Really
    -0.06
     هي
    -0.06
    POSITIVE LOGITS
     forging
    0.07
    \GeneratedValue
    0.07
     kara
    0.07
    .prompt
    0.06
    उ
    0.06
    TPL
    0.06
    指数
    0.06
    ē
    0.06
    HeaderText
    0.06
    REE
    0.06
    Act Density 0.037%

    No Known Activations