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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating quantity or comparison involving numbers

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

    Numbers following "more than" or "nearly"

    np_acts-logits-general · gemini-2.0-flash

    quantities after 'over' or 'than'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thâu
    -0.98
     فريبيس
    -0.95
    GEBURTSDATUM
    -0.95
    WebElementEntity
    -0.90
     ModelExpression
    -0.85
     <=",
    -0.85
     تضيفلها
    -0.84
     tartalomajánló
    -0.83
    Geplaatst
    -0.82
     EconPapers
    -0.81
    POSITIVE LOGITS
     
    0.65
     twenty
    0.63
     thirty
    0.61
     forty
    0.57
     fifty
    0.56
     ten
    0.56
     sixty
    0.55
     eighty
    0.53
     seventy
    0.53
     half
    0.51
    Act Density 0.135%

    No Known Activations