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

    Neuronpedia

    INDEX
    Explanations

    at a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toujours
    0.44
     お知らせ
    0.41
     Portail
    0.40
    मिली
    0.40
     thỏa
    0.39
    蹉
    0.39
     dédi
    0.39
     noget
    0.39
     yǒu
    0.39
     আৰ
    0.39
    POSITIVE LOGITS
    (
    0.40
    »
    0.40
    
    0.39
    H
    0.39
     Ari
    0.38
    䏼
    0.38
    amate
    0.38
    HO
    0.37
    性が
    0.37
    än
    0.37
    Act Density 0.000%

    No Known Activations