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

    Neuronpedia

    INDEX
    Explanations

    unexpected twists in narratives or discussions

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

    explaining circumstances or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.55
     Pingback
    -0.49
    parsedMessage
    -0.47
     Wikimedijinoj
    -0.46
     సౌకర్య
    -0.45
    ✭✭
    -0.44
     Jefus
    -0.43
     RIPRODUZIONE
    -0.41
     berupa
    -0.41
    nofollow
    -0.40
    POSITIVE LOGITS
     admiration
    0.40
     للمعارف
    0.40
    UnitTesting
    0.38
     talent
    0.37
    LLYWOOD
    0.35
     îna
    0.34
     impartial
    0.34
     cha
    0.33
    abha
    0.33
     volte
    0.33
    Act Density 0.324%

    No Known Activations