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

    Neuronpedia

    INDEX
    Explanations

    io, in, inside, within

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਅ
    0.41
    データ
    0.40
     sequência
    0.40
     データ
    0.40
     magnitude
    0.40
    掙
    0.40
    技術
    0.39
     견
    0.39
     점에서
    0.39
     фраг
    0.39
    POSITIVE LOGITS
    heda
    0.44
     Tuning
    0.43
    église
    0.42
     réunis
    0.42
    看看
    0.41
    ners
    0.41
     Ecology
    0.40
    iversary
    0.40
    park
    0.40
    eday
    0.40
    Act Density 0.023%

    No Known Activations