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

    Neuronpedia

    INDEX
    Explanations

    full scale, blown, fledged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    roveň
    0.79
    pped
    0.78
     പദ്ധതി
    0.78
    പോലെ
    0.76
    ২
    0.76
    где
    0.74
     Loại
    0.73
    ಷ್ಟು
    0.72
    ти
    0.72
    soever
    0.72
    POSITIVE LOGITS
    ↵↵
    0.92
    re
    0.68
    不
    0.67
     spinner
    0.64
     baker
    0.64
     flamenco
    0.61
     diagn
    0.60
     regular
    0.59
    :
    0.59
     walker
    0.59
    Act Density 0.027%

    No Known Activations