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

    Neuronpedia

    INDEX
    Explanations

    affirmative expressions and confirmations

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

    end of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.62
     BoxDecoration
    -0.52
     invokingState
    -0.50
     ***!
    -0.42
     tavo
    -0.41
     disambiguazione
    -0.40
     confusión
    -0.40
     зда
    -0.39
    lapsingToolbar
    -0.39
    yelidikan
    -0.39
    POSITIVE LOGITS
     '\\;'
    0.56
     yes
    0.55
     Administrativna
    0.48
    MessageTagHelper
    0.46
    Yes
    0.45
     المعيارى
    0.45
     
    0.45
     Yes
    0.45
     yeah
    0.44
     oprot
    0.44
    Act Density 0.124%

    No Known Activations