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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Počet
    -0.07
    vars
    -0.07
     �
    -0.07
    етич
    -0.06
     مربع
    -0.06
    horia
    -0.06
    漫画
    -0.06
    utta
    -0.06
    _death
    -0.06
     मतलब
    -0.06
    POSITIVE LOGITS
     ''){↵
    0.07
     "}↵
    0.07
     }>
    0.06
    \Blueprint
    0.06
     hl
    0.06
     _{
    0.06
    obuf
    0.06
    tz
    0.06
     #-
    0.06
    "/></
    0.06
    Act Density 0.000%

    No Known Activations