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

    Neuronpedia

    INDEX
    Explanations

    positive expressions related to diversity, ethics, and community values

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

    what is expected or required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.75
    ThroughAttribute
    -0.56
    setupUi
    -0.55
     estekak
    -0.50
    queryInterface
    -0.49
     propOrder
    -0.45
    AndEndTag
    -0.44
     تضيفلها
    -0.42
     iprot
    -0.41
     disponibilités
    -0.41
    POSITIVE LOGITS
    PYX
    0.39
     égale
    0.39
     habet
    0.37
    PostBack
    0.36
    erval
    0.35
     åt
    0.35
     dipendenti
    0.35
     durée
    0.35
     législation
    0.35
     immédi
    0.34
    Act Density 0.023%

    No Known Activations