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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _adjust
    -0.07
     Kavanaugh
    -0.06
     전화
    -0.06
    ی
    -0.06
     phát
    -0.06
    twig
    -0.06
     paras
    -0.06
    adder
    -0.06
    combine
    -0.06
    났
    -0.06
    POSITIVE LOGITS
    /header
    0.07
     ResponseEntity
    0.07
    ーバ
    0.07
     Coupe
    0.07
    =node
    0.07
     obsah
    0.07
     fearless
    0.06
    .Selection
    0.06
    RegularExpression
    0.06
    报名
    0.06
    Act Density 0.001%

    No Known Activations