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

    Neuronpedia

    INDEX
    Explanations

    help with problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    និត
    0.46
    op
    0.45
    (\
    0.43
     tân
    0.40
    _{(
    0.40
    ሆነ
    0.39
    they
    0.39
    '$.
    0.39
    述
    0.39
     coll
    0.38
    POSITIVE LOGITS
     fermé
    0.48
    ılan
    0.47
     هزار
    0.47
    二维码
    0.46
    ı
    0.46
     unnamed
    0.46
     easier
    0.45
    すでに
    0.45
    nań
    0.44
    namento
    0.44
    Act Density 0.002%

    No Known Activations