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

    Neuronpedia

    INDEX
    Explanations

    religious phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     இலவச
    0.45
     ఫలి
    0.42
     работо
    0.42
     இழ
    0.41
    唪
    0.41
     உங்கள்
    0.40
     ಏಕೆಂದರೆ
    0.40
     செயல்ப
    0.40
     زیرمه
    0.40
     ඔබේ
    0.40
    POSITIVE LOGITS
    ud
    0.44
     was
    0.43
    head
    0.41
     of
    0.40
    X
    0.40
    q
    0.39
    ch
    0.38
     from
    0.38
     came
    0.38
    was
    0.38
    Act Density 0.005%

    No Known Activations