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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating questions or uncertainty

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

    even if, though

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WebVitals
    -0.59
    LookAnd
    -0.59
    Hentet
    -0.56
     calendriers
    -0.54
     Rental
    -0.53
     ویکی‌پدیای
    -0.52
    AndEndTag
    -0.51
    ValueStyle
    -0.50
     cherchés
    -0.50
    #+#
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.35
     OTHERWISE
    0.32
    fillType
    0.30
     membunuh
    0.29
     toch
    0.29
     îna
    0.28
     الحره
    0.28
    (&:
    0.27
    otherwise
    0.27
     Bestimmung
    0.27
    Act Density 1.559%

    No Known Activations