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

    Neuronpedia

    INDEX
    Explanations

    entering numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sacchar
    0.45
     Polyester
    0.42
    ിക്കുന്നു
    0.41
     polyester
    0.41
     অধিকাংশই
    0.41
     Wirtschaft
    0.41
     Atmosphäre
    0.41
     गहरी
    0.40
     ekonomi
    0.40
    toDouble
    0.39
    POSITIVE LOGITS
     integers
    0.63
     integer
    0.61
    整数
    0.61
    Integer
    0.60
     numerals
    0.55
    integer
    0.54
     numeral
    0.54
     numbers
    0.54
     whole
    0.52
     number
    0.51
    Act Density 0.015%

    No Known Activations