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

    Neuronpedia

    INDEX
    Explanations

    Exit loop

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    많은
    0.52
    Its
    0.51
    人们
    0.50
    ITS
    0.49
    Various
    0.46
    人們
    0.46
    Their
    0.45
     innumerable
    0.44
    Systems
    0.43
     bepaalde
    0.43
    POSITIVE LOGITS
     them
    0.70
     the
    0.61
     manualmente
    0.59
     novamente
    0.59
     remaining
    0.57
     your
    0.56
     nuovamente
    0.56
     desired
    0.55
     ponownie
    0.55
     him
    0.54
    Act Density 1.168%

    No Known Activations