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

    Neuronpedia

    INDEX
    Explanations

    categorizing lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     predominate
    0.45
     chandeliers
    0.42
    フグ
    0.41
     emphasise
    0.41
    ਤ
    0.40
     drawRight
    0.39
     Kritik
    0.38
    뀔
    0.38
     glPushMatrix
    0.38
    renees
    0.38
    POSITIVE LOGITS
     vrát
    0.38
    ・
    0.38
     करने
    0.38
     `@
    0.37
     сих
    0.36
     شده
    0.36
    va
    0.35
    '
    0.35
     شدہ
    0.34
    _
    0.33
    Act Density 0.061%

    No Known Activations