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

    Neuronpedia

    INDEX
    Explanations

    foreign words", ", "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     geolocation
    1.12
     soybean
    1.07
     리
    1.07
     neurological
    1.05
     Oracle
    1.03
     geospatial
    1.02
     vampire
    1.00
     mathematics
    1.00
     ﺍ
    0.96
     Mathematics
    0.95
    POSITIVE LOGITS
    ฯ
    0.88
    <unused63>
    0.75
    <unused60>
    0.74
     ζωή
    0.74
     opět
    0.71
    כם
    0.65
    مكن
    0.64
    قع
    0.64
    wechsl
    0.63
     gelungen
    0.63
    Act Density 0.102%

    No Known Activations