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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements and statistical data related to various subjects

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

    Numbers followed by commas or "thousand", "million"

    np_acts-logits-general · gemini-2.0-flash

    large quantities and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    şiv
    -0.61
    delning
    -0.58
     Chwiliwch
    -0.52
    romycin
    -0.49
    holdet
    -0.48
    WriteLiteral
    -0.48
    unjukkan
    -0.47
     cạnh
    -0.47
    ėse
    -0.47
    おすすめです
    -0.47
    POSITIVE LOGITS
     (!)
    0.87
     total
    0.80
    (!)
    0.79
     hundred
    0.79
     thousand
    0.77
    TagMode
    0.77
     acres
    0.72
     souls
    0.70
     pieces
    0.69
     человек
    0.68
    Act Density 0.358%

    No Known Activations