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

    Neuronpedia

    INDEX
    Explanations

    key terms and concepts related to specific categories or primary subjects in a document

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

    main followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Autorisations
    -0.54
    utives
    -0.52
    səhifə
    -0.48
    InjectAttribute
    -0.48
    afficheront
    -0.47
    liferay
    -0.47
    ReusableCell
    -0.44
    TRAILING
    -0.43
     sleepers
    -0.43
    ksikon
    -0.42
    POSITIVE LOGITS
     main
    1.42
    main
    1.20
     głów
    1.18
     Main
    1.16
    Main
    1.16
     utama
    1.13
     principale
    1.12
     principaux
    1.10
    MAIN
    1.09
     principali
    1.09
    Act Density 0.054%

    No Known Activations