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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases that express uncertainty or questioning, particularly in collaborative or decision-making contexts

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

    complex analysis and explanation

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron activates on content-bearing, informative tokens (important nouns/verbs/adjectives and discourse-focus words) rather than on function words.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.71
    Бахар
    -0.68
    BeginContext
    -0.66
     lenker
    -0.63
     المعيارى
    -0.56
    contentLoaded
    -0.54
    ᅠ
    -0.52
     ſind
    -0.50
    styleType
    -0.50
    mergeFrom
    -0.50
    POSITIVE LOGITS
    fromnode
    0.47
    复杂的
    0.40
     complex
    0.39
     complexo
    0.37
     thoughtful
    0.36
    复杂
    0.36
     compleja
    0.36
     active
    0.36
    ftagPool
    0.34
    Activités
    0.33
    Act Density 0.110%

    No Known Activations