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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to people or organizations

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

    person and company names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.57
    ftagPool
    -0.56
    RefNanny
    -0.54
    ValueStyle
    -0.47
     nahilalakip
    -0.47
    Personendaten
    -0.44
     propOrder
    -0.43
    XmlAccessorType
    -0.43
     oprot
    -0.42
     EconPapers
    -0.42
    POSITIVE LOGITS
     smtplib
    0.52
    upb
    0.49
     AppBundle
    0.46
    textwidth
    0.45
     bezeichneter
    0.45
    SceneManagement
    0.43
     $_"
    0.43
     CUCET
    0.42
    writerow
    0.42
    providedIn
    0.41
    Act Density 1.555%

    No Known Activations