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

    Neuronpedia

    INDEX
    Explanations

    what asks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    soever
    1.42
    tan
    1.34
    ுள்ளது
    1.25
    tion
    1.23
    tı
    1.20
    treated
    1.17
    tions
    1.16
    yyyyyyyy
    1.15
    thed
    1.14
    ுள்ள
    1.09
    POSITIVE LOGITS
    id
    1.59
    ال
    1.38
    पणे
    1.25
     także
    1.19
    al
    1.17
    es
    1.14
    го
    1.14
    í
    1.13
    ї
    1.12
     ƙ
    1.10
    Act Density 0.286%

    No Known Activations