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

    Neuronpedia

    INDEX
    Explanations

    references to sections and organization within a document

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

    in section or step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.46
     bores
    -0.42
    Brainz
    -0.41
     Cavendish
    -0.40
    Portail
    -0.40
     hivyo
    -0.40
    mpagne
    -0.39
    ereka
    -0.39
    évaluateur
    -0.39
     pawns
    -0.39
    POSITIVE LOGITS
    Билгалдахарш
    0.51
     Chapter
    0.50
    InSection
    0.48
    exitRule
    0.48
     defaultstate
    0.47
    ⓧ
    0.47
     Appendix
    0.46
    enumi
    0.44
    帖最后由
    0.44
    ThemeOverlay
    0.43
    Act Density 0.127%

    No Known Activations