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

    Neuronpedia

    INDEX
    Explanations

    notes and technical details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺍ
    1.37
     confounding
    1.31
    wości
    1.30
     daerah
    1.27
     downfall
    1.18
     Moż
    1.16
    ਼
    1.15
     кы
    1.12
     tartış
    1.12
     नवी
    1.11
    POSITIVE LOGITS
    na
    1.36
    soever
    1.34
    ni
    1.29
    n
    1.18
    nnnn
    1.14
    на
    1.14
    oms
    1.10
     accessori
    1.10
     অতএব
    1.10
    chen
    1.08
    Act Density 0.002%

    No Known Activations