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

    Neuronpedia

    INDEX
    Explanations

    quoted speech or dialogue

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

    closing quotation marks followed by pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.66
    ArgsConstructor
    -0.65
    はじめに
    -0.64
     podjela
    -0.61
     endblock
    -0.61
     kasarigan
    -0.60
    Portail
    -0.59
    :✨
    -0.59
     wireType
    -0.59
     betweenstory
    -0.58
    POSITIVE LOGITS
     preguntó
    0.39
    脚注の使い方
    0.36
    FXML
    0.35
     saying
    0.35
     preocupar
    0.33
     déclare
    0.33
     demanding
    0.32
     "
    0.30
     Yesus
    0.30
     asked
    0.29
    Act Density 0.023%

    No Known Activations