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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships between factors and outcomes

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

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.55
    balleur
    -0.42
    Архівовано
    -0.37
     Canaan
    -0.36
     cartaz
    -0.36
    dyž
    -0.36
    oredCriteria
    -0.35
    TagNumber
    -0.35
     يتيمه
    -0.35
     verzichten
    -0.35
    POSITIVE LOGITS
    QMetaType
    0.56
    hyrchwyd
    0.48
     ویکی‌پدی
    0.46
     EconPapers
    0.45
    PerformLayout
    0.44
    優
    0.43
    endpush
    0.41
    MLLoader
    0.40
     IDEOGRAPH
    0.40
    HideFlags
    0.40
    Act Density 0.261%

    No Known Activations