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

    Neuronpedia

    INDEX
    Explanations

    huevo precede

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.47
     dello
    0.45
    י
    0.44
    ro
    0.44
     bæ
    0.44
     S
    0.43
     up
    0.43
     ev
    0.42
    ಿ
    0.42
     en
    0.41
    POSITIVE LOGITS
     взаимодей
    0.54
     версия
    0.52
     категории
    0.50
     версии
    0.50
     الغير
    0.48
    䒑
    0.48
    琟
    0.47
     глава
    0.47
    月份
    0.47
    зия
    0.46
    Act Density 0.002%

    No Known Activations