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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kost
    -0.08
     benign
    -0.08
    歌
    -0.08
    /style
    -0.08
    िक्ष
    -0.08
     OE
    -0.07
     latter
    -0.07
     privilege
    -0.07
     spaz
    -0.07
     verr
    -0.07
    POSITIVE LOGITS
    Pct
    0.11
     percentile
    0.11
     Percent
    0.11
     ശതമ
    0.10
    Percent
    0.10
    .Percent
    0.10
    (percent
    0.10
    percent
    0.10
    percentage
    0.09
     percentage
    0.09
    Act Density 0.056%

    No Known Activations