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

    Neuronpedia

    INDEX
    Explanations

    code/math/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     and
    -0.93
    estacks
    -0.56
    참고
    -0.51
     Table
    -0.46
    name
    -0.45
    Table
    -0.44
    ponses
    -0.44
    amate
    -0.44
    findpost
    -0.43
    DidLoad
    -0.43
    POSITIVE LOGITS
    awtextra
    0.90
     @"/
    0.81
    ConstraintMaker
    0.78
    IsContent
    0.77
     فريبيس
    0.76
    AndEndTag
    0.76
     مرئيه
    0.74
    makeConstraints
    0.74
    IBarButtonItem
    0.72
     समीक्षाओं
    0.72
    Act Density 0.181%

    No Known Activations