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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Char
    -0.07
     tabBar
    -0.07
    加盟店
    -0.07
     mainBundle
    -0.07
    ,)
    -0.07
     atol
    -0.07
    M
    -0.07
    Tex
    -0.06
     View
    -0.06
    不满
    -0.06
    POSITIVE LOGITS
    ï
    0.07
    文化创意
    0.07
    legacy
    0.07
    обыти
    0.07
    kształc
    0.07
    légi
    0.07
     erotici
    0.07
    特意
    0.07
     Tiến
    0.06
     seçil
    0.06
    Act Density 0.008%

    No Known Activations