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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate dialogue or questioning in the text

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

    dialogue endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miniaturka
    -0.66
     régional
    -0.65
     للاسماء
    -0.65
     ilustracja
    -0.60
     bluzka
    -0.60
     kurtka
    -0.59
     Polri
    -0.59
     présidentielle
    -0.59
     actualidad
    -0.57
     productivo
    -0.57
    POSITIVE LOGITS
    #
    0.52
     spo
    0.46
    StructEnd
    0.44
    spo
    0.42
    buttonShape
    0.41
     Spo
    0.40
     Ste
    0.40
     Roskov
    0.40
    ///</
    0.39
    CloseOperation
    0.39
    Act Density 0.019%

    No Known Activations