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

    Neuronpedia

    INDEX
    Explanations

    learning, reading, understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.54
     and
    0.52
     మరియు
    0.45
    &-
    0.45
    cl
    0.44
    或
    0.42
    和
    0.41
     ও
    0.41
     và
    0.40
    และ
    0.40
    POSITIVE LOGITS
     Lernen
    0.44
     przepis
    0.43
     mempelajari
    0.42
    阅读
    0.42
     öğrenc
    0.41
    لوث
    0.41
     чле
    0.41
    这本书
    0.41
     рецен
    0.41
    筚
    0.40
    Act Density 0.002%

    No Known Activations