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

    Neuronpedia

    INDEX
    Explanations

    alternate names/explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     converters
    -0.07
     Haram
    -0.07
    [^
    -0.06
    _activation
    -0.06
    нки
    -0.06
     Hurricanes
    -0.06
    .assertAlmostEqual
    -0.06
    +-+-
    -0.06
    _activate
    -0.06
     پیک
    -0.06
    POSITIVE LOGITS
    орту
    0.07
    _fit
    0.07
    清楚
    0.06
    Renderer
    0.06
    ленно
    0.06
     Nevada
    0.06
    MESSAGE
    0.06
    umd
    0.06
    oka
    0.06
    огу
    0.06
    Act Density 0.090%

    No Known Activations