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

    Neuronpedia

    INDEX
    Explanations

    constructs related to formatting numbers and date/time representations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Conversions or calculations involving numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantity conversions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.62
     cousin
    -0.62
    contentLoaded
    -0.59
     Monark
    -0.59
     ujednoznacz
    -0.57
    PerformLayout
    -0.57
    Cousin
    -0.56
    HttpDelete
    -0.55
    cous
    -0.53
    émie
    -0.53
    POSITIVE LOGITS
     digit
    1.07
     digits
    1.02
    digit
    0.96
    Digit
    0.94
     Digit
    0.91
    digits
    0.81
    Digits
    0.80
     Dig
    0.75
     díg
    0.75
     DIGIT
    0.74
    Act Density 0.332%

    No Known Activations