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

    Neuronpedia

    INDEX
    Explanations

    `csv.reader(` `Naive Bayes`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tengas
    1.25
     meio
    1.20
     Stewardship
    1.20
    اً
    1.16
     tengan
    1.16
     nahin
    1.16
    cknowled
    1.14
     Ciebie
    1.14
     three
    1.13
     patru
    1.13
    POSITIVE LOGITS
    نا
    1.16
    le
    1.14
    나
    1.14
    ס
    1.06
    OS
    1.03
    РО
    1.01
    АС
    1.00
    ENT
    0.98
    OpenGL
    0.98
    ishly
    0.97
    Act Density 0.003%

    No Known Activations