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

    Neuronpedia

    INDEX
    Explanations

    quantifiable comparisons and statistical information

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

    Quantity comparisons (more/less, twice/times as many)

    np_acts-logits-general · gemini-2.0-flash

    quantity and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.63
     HasFactory
    -0.63
    RegressionTest
    -0.61
     externi
    -0.60
    FormTagHelper
    -0.58
    IsContent
    -0.57
    ที่ดี
    -0.57
    XtraGrid
    -0.57
    AndEndTag
    -0.57
     متعلقه
    -0.57
    POSITIVE LOGITS
     enough
    1.43
     more
    1.39
     plenty
    1.18
    enough
    1.17
     lots
    1.14
     suffisamment
    1.13
     fewer
    1.11
     less
    1.07
     Enough
    1.07
     ENOUGH
    1.07
    Act Density 0.642%

    No Known Activations