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

    Neuronpedia

    INDEX
    Explanations

    quantitative details related to experimental results and measurements

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

    Numbers (often 1, 10, 100)

    np_acts-logits-general · gemini-2.0-flash

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.97
     مرئيه
    -0.73
    ⓧ
    -0.73
     nearly
    -0.66
     Nearly
    -0.66
     almost
    -0.65
    nearly
    -0.65
    almost
    -0.62
    NewUrlParser
    -0.62
    tvguidetime
    -0.62
    POSITIVE LOGITS
     ten
    1.04
     Ten
    0.89
    Ten
    0.87
     hundred
    0.81
     TEN
    0.81
     Hundred
    0.73
    Hundred
    0.71
    TEN
    0.70
    hundred
    0.69
     zehn
    0.67
    Act Density 0.771%

    No Known Activations