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

    Neuronpedia

    INDEX
    Explanations

    radio button

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pero
    -2.72
    </em>
    -2.67
     But
    -2.41
    ）
    -2.19
    でも
    -2.16
     लेकिन
    -2.13
     *
    -2.09
     of
    -2.02
    me
    -2.02
    ↵
    -2.02
    POSITIVE LOGITS
    ጧ
    2.69
    Ꭳ
    2.50
    媼
    2.45
    ዒ
    2.39
     imprimer
    2.28
    ेशा
    2.25
    ܇
    2.25
    壜
    2.17
    鮃
    2.17
     chocs
    2.17
    Act Density 0.001%

    No Known Activations