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

    Neuronpedia

    INDEX
    Explanations

    references to authority and guidance in various contexts

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

    just or could

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Viungo
    -0.64
     ModelExpression
    -0.62
    ConstraintMaker
    -0.61
    IBOutlet
    -0.60
     Administrativna
    -0.60
     للاسماء
    -0.59
    AddTagHelper
    -0.59
    ContentAsync
    -0.59
     مرئيه
    -0.57
     незавершена
    -0.55
    POSITIVE LOGITS
     عاما
    0.32
    ponses
    0.32
     desselben
    0.31
     saja
    0.30
    ftance
    0.30
    krankungen
    0.29
    esía
    0.29
    evos
    0.29
    Enfin
    0.29
    /**
    0.28
    Act Density 0.123%

    No Known Activations