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

    Neuronpedia

    INDEX
    Explanations

    he and his

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     తమ
    0.25
     தங்கள்
    0.25
     הם
    0.24
    都知道
    0.24
    都是
    0.24
    都在
    0.24
    ходили
    0.23
    న్నారు
    0.23
     ہوں
    0.23
    Have
    0.22
    POSITIVE LOGITS
     himself
    0.46
     his
    0.33
    eding
    0.32
     его
    0.32
    aving
    0.30
    aved
    0.29
    arken
    0.29
     그의
    0.29
     wears
    0.28
    ctor
    0.28
    Act Density 0.042%

    No Known Activations