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

    Neuronpedia

    INDEX
    Explanations

    billions of words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.97
     any
    0.87
     an
    0.83
     любой
    0.73
     some
    0.70
     atan
    0.67
    まさ
    0.67
    して
    0.66
     أي
    0.66
    ographic
    0.64
    POSITIVE LOGITS
    s
    0.92
    ों
    0.78
     społ
    0.67
     sclerosis
    0.66
     sleepers
    0.66
    개가
    0.66
     hectares
    0.64
     (>
    0.64
     Bedrooms
    0.63
    אר
    0.63
    Act Density 0.049%

    No Known Activations