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

    Neuronpedia

    INDEX
    Explanations

    academic and research-related activities and methodologies

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

    that introduce descriptions or outlines

    np_acts-logits-general · gemini-2.0-flash

    describing how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Arkivert
    -0.77
     NDEBUG
    -0.77
    MigrationBuilder
    -0.70
     OMITBAD
    -0.70
    SequentialGroup
    -0.68
     ویکی‌پدیای
    -0.67
     tartalomajánló
    -0.65
    Portale
    -0.62
    getValueAt
    -0.61
     JpaRepository
    -0.60
    POSITIVE LOGITS
     how
    0.78
     ways
    0.64
     why
    0.54
     azok
    0.52
    how
    0.52
     briefly
    0.50
    HtmlAttribute
    0.49
     the
    0.48
     hvordan
    0.48
    ($__
    0.48
    Act Density 0.548%

    No Known Activations