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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     three
    -0.88
     two
    -0.87
     four
    -0.79
     seven
    -0.69
     eight
    -0.68
     five
    -0.67
     nine
    -0.66
     six
    -0.65
    ,
    -0.65
    .
    -0.59
    POSITIVE LOGITS
    queryInterface
    0.87
    حياته
    0.86
    ✨:
    0.83
    حياتها
    0.81
     Савезне
    0.80
    featureID
    0.79
    bibfield
    0.78
    بوابة
    0.78
    Tikang
    0.77
    HtmlAttribute
    0.77
    Act Density 0.230%

    No Known Activations