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

    Neuronpedia

    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Our
    0.45
     Tr
    0.42
     అత్య
    0.42
     TR
    0.41
     Patricia
    0.41
    ̸
    0.41
     Ticket
    0.40
     EVERYTHING
    0.40
     Por
    0.39
     Ihr
    0.39
    POSITIVE LOGITS
     ۱۰
    0.53
     पांच
    0.53
    foo
    0.52
     five
    0.52
     fives
    0.52
     पाच
    0.51
     cinque
    0.50
    五个
    0.50
    five
    0.49
     ۵
    0.49
    Act Density 0.050%

    No Known Activations