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

    Neuronpedia

    INDEX
    Explanations

    effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,and
    -0.08
    玄
    -0.07
    作为一名
    -0.07
    reme
    -0.07
     ngày
    -0.07
     Learning
    -0.07
     CHARACTER
    -0.06
    %"),↵
    -0.06
    绕
    -0.06
    必要があります
    -0.06
    POSITIVE LOGITS
    (interval
    0.07
     Const
    0.07
     decks
    0.07
     neural
    0.06
     By
    0.06
     Hal
    0.06
     Leafs
    0.06
    onald
    0.06
    领域
    0.06
     ole
    0.06
    Act Density 0.000%

    No Known Activations