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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and their citations

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

    URLs and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enfans
    -0.54
    RequestDto
    -0.44
     udaler
    -0.44
     Segurança
    -0.43
    RTEX
    -0.43
     pitié
    -0.42
    Ӕ
    -0.42
    berapa
    -0.42
    jaqueta
    -0.42
    jaardag
    -0.41
    POSITIVE LOGITS
    audiovisuel
    0.45
    GOTREF
    0.44
    pageId
    0.43
     للاسماء
    0.42
    idados
    0.42
     ivelany
    0.42
    Huile
    0.41
    QMetaType
    0.41
    defineProperty
    0.39
    hyrchwyd
    0.39
    Act Density 0.002%

    No Known Activations