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

    Neuronpedia

    INDEX
    Explanations

    mathematics/statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    瓢
    -0.07
    孝
    -0.07
    禹
    -0.07
    upo
    -0.07
     curtain
    -0.06
     Purs
    -0.06
    ṝ
    -0.06
    (ln
    -0.06
     endeavors
    -0.06
    ед
    -0.06
    POSITIVE LOGITS
    纳米
    0.07
    libft
    0.07
    OU
    0.06
    **)
    0.06
    Cow
    0.06
    _candidate
    0.06
     Rate
    0.06
    ."_
    0.06
    ')."
    0.06
    -friendly
    0.06
    Act Density 0.023%

    No Known Activations