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

    Neuronpedia

    INDEX
    Explanations

    describing or framing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     แล้ว
    0.52
     όπως
    0.48
     그리고
    0.47
     ហើយ
    0.47
     säger
    0.47
     Dazu
    0.46
     ይቀ
    0.46
     然后
    0.45
     ထ
    0.45
     وتح
    0.45
    POSITIVE LOGITS
     being
    1.02
     having
    1.00
    being
    0.98
     étant
    0.95
    having
    0.87
     olev
    0.75
     needing
    0.73
    étant
    0.71
     requiring
    0.67
    Being
    0.66
    Act Density 0.061%

    No Known Activations