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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avent
    -0.08
    тим
    -0.06
    xb
    -0.06
    Retry
    -0.06
    -number
    -0.06
    орд
    -0.06
    lim
    -0.06
    ;↵↵↵
    -0.06
    暂
    -0.06
    "math
    -0.06
    POSITIVE LOGITS
     LESS
    0.06
    _UNICODE
    0.06
     จำ
    0.06
     heiß
    0.06
     RULE
    0.06
     graduation
    0.06
     tariff
    0.06
     scandal
    0.05
     jit
    0.05
     представляет
    0.05
    Act Density 0.004%

    No Known Activations