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

    Neuronpedia

    INDEX
    Explanations

    positive sentiments or descriptors regarding experiences and things

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

    positive adjectives followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.62
     ویکی‌پدی
    -0.58
    LookAnd
    -0.56
    ftagPool
    -0.54
    Personendaten
    -0.50
    IntoConstraints
    -0.47
     للاسماء
    -0.47
    ✥
    -0.45
    EDEFAULT
    -0.45
    adaptiveStyles
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.56
     '\\;'
    0.54
    Cordialement
    0.47
    IRD
    0.42
    évaluateur
    0.41
    Incredible
    0.40
    intellij
    0.40
    şiv
    0.39
     estekak
    0.37
    Protos
    0.37
    Act Density 0.006%

    No Known Activations