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

    Neuronpedia

    INDEX
    Explanations

    independent existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सिलसिले
    0.47
    锼
    0.43
    раз
    0.43
    еру
    0.41
    制御
    0.41
     контроля
    0.41
     configurações
    0.40
    原有
    0.40
    作業
    0.39
     издели
    0.39
    POSITIVE LOGITS
     speed
    0.54
     female
    0.53
     without
    0.50
     student
    0.49
     distracted
    0.49
     pod
    0.47
     Without
    0.47
     impacted
    0.47
     infected
    0.47
    pless
    0.46
    Act Density 0.031%

    No Known Activations