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

    Neuronpedia

    INDEX
    Explanations

    listing items with 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     พระเจ้า
    0.36
     മരണ
    0.36
     absur
    0.36
     કારણે
    0.35
     wrongdoing
    0.35
     言っ
    0.34
     berühm
    0.34
    恐惧
    0.34
     ሰዎች
    0.33
     เช่น
    0.33
    POSITIVE LOGITS
     Pan
    0.38
     approximately
    0.38
     three
    0.35
     base
    0.33
    pan
    0.33
     Line
    0.33
     approx
    0.33
     Base
    0.32
     vertical
    0.32
     and
    0.31
    Act Density 0.294%

    No Known Activations