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

    Neuronpedia

    INDEX
    Explanations

    quantitative data represented in a tabular format

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

    Numbers starting with zero

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units or p-values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.93
     ostavi
    -0.73
     gré
    -0.69
    Становништво
    -0.65
    defineProperty
    -0.65
    InlineData
    -0.64
     Sommers
    -0.63
     McCar
    -0.63
    iddhar
    -0.62
    arina
    -0.62
    POSITIVE LOGITS
    0
    1.13
     Eury
    0.65
    retweeted
    0.61
    Edith
    0.60
    reciate
    0.59
     المتحدة
    0.59
    troppo
    0.59
    +#+#
    0.58
     seguido
    0.58
    ０
    0.58
    Act Density 0.518%

    No Known Activations