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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating non-affiliation or independence from organizations or entities

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

    official or independent affiliation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '{@
    -0.65
     OMITBAD
    -0.56
    dafx
    -0.51
    цездатний
    -0.51
    ngdoc
    -0.50
     समीक्षक
    -0.49
    SharedDtor
    -0.49
     Réponses
    -0.49
    Personensuche
    -0.48
    complexContent
    -0.47
    POSITIVE LOGITS
     independent
    0.35
    HtmlAttribute
    0.34
     encouragement
    0.34
     unaff
    0.33
     independ
    0.33
     official
    0.33
    èlement
    0.33
     officiel
    0.32
     unrelated
    0.32
     officielle
    0.32
    Act Density 0.246%

    No Known Activations