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

    Neuronpedia

    INDEX
    Explanations

    growth potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     d
    0.62
     is
    0.51
     Ros
    0.47
     middle
    0.46
     Dancing
    0.45
     scler
    0.45
     e
    0.45
     الس
    0.45
     le
    0.44
     @
    0.44
    POSITIVE LOGITS
    рта
    0.57
    чом
    0.54
    чаем
    0.52
    盹
    0.51
     sẵn
    0.49
    рас
    0.49
     prêts
    0.49
    тр
    0.48
    з
    0.48
     près
    0.48
    Act Density 0.003%

    No Known Activations