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

    Neuronpedia

    INDEX
    Explanations

    technical keywords and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ట్‌
    0.53
     delineation
    0.47
     для
    0.47
     swatch
    0.47
     outta
    0.47
     detour
    0.46
     spreader
    0.46
     rearing
    0.45
    )">
    0.45
    тисти
    0.45
    POSITIVE LOGITS
    re
    0.66
    an
    0.63
    مو
    0.63
    सबसे
    0.61
    one
    0.59
    ان
    0.59
    at
    0.58
    ad
    0.58
    આ
    0.58
    ्रू
    0.58
    Act Density 1.003%

    No Known Activations