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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical references in the text

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

    The number five

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eighth
    -0.68
    Портал
    -0.61
     eighties
    -0.57
    nestjs
    -0.56
    ArgumentParser
    -0.56
     Seventy
    -0.56
     resourceCulture
    -0.56
     Eight
    -0.54
     Zwe
    -0.53
     Seven
    -0.53
    POSITIVE LOGITS
    5
    0.82
     fifth
    0.72
     five
    0.70
    五
    0.66
     quinto
    0.65
     cinque
    0.65
    五个
    0.64
     cinq
    0.63
    five
    0.63
     cinco
    0.61
    Act Density 0.454%

    No Known Activations