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

    Neuronpedia

    INDEX
    Explanations

    BS followed by numbers or "a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.46
    punt
    0.41
    debut
    0.41
    Activity
    0.40
     debut
    0.40
    se
    0.40
    cop
    0.39
    sw
    0.39
     nave
    0.39
    p
    0.38
    POSITIVE LOGITS
    स्फी
    0.48
     Yed
    0.43
    mobilpay
    0.42
     প্রতিষ্ঠাতা
    0.42
     औपचारिक
    0.41
    䒽
    0.41
     Đế
    0.41
    پلز
    0.40
    朤
    0.40
    Wedgwood
    0.40
    Act Density 0.002%

    No Known Activations