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

    Neuronpedia

    INDEX
    Explanations

    reports and news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $$$
    -0.07
     lut
    -0.07
    ersen
    -0.06
     audit
    -0.06
    .My
    -0.06
    -sdk
    -0.06
     wast
    -0.06
     alım
    -0.06
    familia
    -0.06
    Examples
    -0.06
    POSITIVE LOGITS
    WIDTH
    0.07
    ()])↵
    0.06
    ┴
    0.06
    '),↵
    0.06
     přesvěd
    0.06
    كه
    0.06
    .isHidden
    0.06
     سكان
    0.06
    0.06
    setting
    0.06
    Act Density 0.026%

    No Known Activations