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

    Neuronpedia

    INDEX
    Explanations

    terms related to correctness and suitability

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

    right kind of thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IonicModule
    -0.50
    出版年
    -0.43
     possessor
    -0.42
    isContained
    -0.41
    ConverterFactory
    -0.40
    IATA
    -0.39
    HtmlAttribute
    -0.39
     GoFundMe
    -0.38
     existência
    -0.38
     Patreon
    -0.37
    POSITIVE LOGITS
     right
    0.67
    Right
    0.65
     Right
    0.61
    RIGHT
    0.59
     giusto
    0.59
     giusti
    0.58
    right
    0.57
     RIGHT
    0.57
    suitable
    0.56
     richtigen
    0.56
    Act Density 0.006%

    No Known Activations