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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or clarity regarding decisions and outcomes

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

    Describes something as obvious, simple, or natural

    np_acts-logits-general · gemini-2.0-flash

    easy, natural, obvious decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MongoClient
    -0.57
     nahilalakip
    -0.52
     мәкал
    -0.51
    MemoryWarning
    -0.49
    SourceChecksum
    -0.49
     Grind
    -0.48
    cemment
    -0.48
    setContentView
    -0.48
    HasAnnotation
    -0.47
    addCriterion
    -0.47
    POSITIVE LOGITS
     obvious
    0.80
     naturellement
    0.80
     naturally
    0.79
     naturalmente
    0.77
     logically
    0.75
     intuitively
    0.72
     évidence
    0.71
     unsur
    0.71
     effortlessly
    0.71
    ISupport
    0.71
    Act Density 0.198%

    No Known Activations