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

    Neuronpedia

    INDEX
    Explanations

    instances of negation and expressions of disapproval

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

    References/citations, often with numbers/years

    np_acts-logits-general · gemini-2.0-flash

    years and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.97
     CreateTagHelper
    -0.83
    adaptiveStyles
    -0.78
    bootstrapcdn
    -0.72
     مشين
    -0.72
    writeFieldEnd
    -0.71
    UnusedPrivate
    -0.70
     arşivlendi
    -0.70
     lenker
    -0.69
     Chwiliwch
    -0.69
    POSITIVE LOGITS
     közül
    0.59
    breviations
    0.58
     Monfieur
    0.57
    oredCriteria
    0.56
     carvings
    0.56
     suivants
    0.56
     sutures
    0.54
     respectivement
    0.54
     réunis
    0.53
     universale
    0.53
    Act Density 0.052%

    No Known Activations