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

    Neuronpedia

    INDEX
    Explanations

    numbers and digit operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Allergy
    0.49
     curfew
    0.47
     Lagoon
    0.46
     çat
    0.46
    StarService
    0.46
     Luffy
    0.45
     unlawfully
    0.45
     varieg
    0.45
    ເວ
    0.44
     alerg
    0.44
    POSITIVE LOGITS
     digits
    1.23
     decimal
    1.09
    digits
    1.09
    Digits
    1.07
     digit
    0.95
     decimals
    0.89
     DECIMAL
    0.89
    Decimal
    0.88
    decimal
    0.88
     numerals
    0.87
    Act Density 0.182%

    No Known Activations