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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to quantities, such as counts or percentages

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

    large quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ReusableCell
    -0.48
     peines
    -0.42
     pouvoit
    -0.42
    sizeCache
    -0.41
    SourceChecksum
    -0.41
    MIDDLEWARE
    -0.40
     étoient
    -0.40
     enfans
    -0.40
     ویکی‌پدی
    -0.39
    UserScript
    -0.39
    POSITIVE LOGITS
     dozens
    0.77
     Several
    0.77
    Numerous
    0.76
    Several
    0.76
     several
    0.73
    several
    0.73
     Numerous
    0.72
    Hundreds
    0.68
     numerous
    0.68
    enumi
    0.67
    Act Density 0.050%

    No Known Activations