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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries seeking information or clarification

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

    Following question words (if, can)

    np_acts-logits-general · gemini-2.0-flash

    asking if or about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gegenteil
    -0.54
     оригіналу
    -0.54
    bitField
    -0.50
     queſta
    -0.48
     varandra
    -0.47
    engagent
    -0.47
     незавершена
    -0.46
    +#+
    -0.46
     itſelf
    -0.46
     perfección
    -0.45
    POSITIVE LOGITS
     inquired
    0.52
     enquired
    0.47
    Carriera
    0.47
     Gay
    0.45
    Gay
    0.45
    figured
    0.44
     clarify
    0.42
     inquire
    0.41
    uyện
    0.41
     clarified
    0.40
    Act Density 0.330%

    No Known Activations