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

    Neuronpedia

    INDEX
    Explanations

    terms related to eligibility and selection criteria in various contexts

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

    inclusion criteria

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.52
    锈钢
    -0.48
     stället
    -0.47
    Jîn
    -0.46
    ImageContext
    -0.46
    igata
    -0.45
     Keuangan
    -0.45
    WriteAttribute
    -0.44
    FFIX
    -0.44
     OMITBAD
    -0.43
    POSITIVE LOGITS
    RenderAtEndOf
    0.43
    adaptiveStyles
    0.43
    UnusedPrivate
    0.41
     للاسماء
    0.38
     خارجية
    0.37
     NSCoder
    0.36
    ècie
    0.36
     Features
    0.36
    saraba
    0.35
     features
    0.35
    Act Density 0.292%

    No Known Activations