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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    传奇游戏
    -0.08
    passport
    -0.08
    kode
    -0.07
    台上
    -0.07
    ubble
    -0.07
    在传奇
    -0.07
     confirmPassword
    -0.06
     bakeka
    -0.06
     Knicks
    -0.06
    ແ
    -0.06
    POSITIVE LOGITS
    _SEL
    0.08
    (Output
    0.07
    _district
    0.07
     Occupation
    0.07
     September
    0.07
    -----------
    0.07
    (dir
    0.07
     perfection
    0.06
     Founded
    0.06
     inferred
    0.06
    Act Density 0.001%

    No Known Activations