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

    Neuronpedia

    INDEX
    Explanations

    AI assistant

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

    The neuron strongly activates on the acronym “AI.”

    oai_token-act-pair · o4-miniTriggered by @yooniel31

    mentions of artificial intelligence, especially references to AI assistants, models, or AI-powered technologies.

    oai_token-act-pair · gpt-5Triggered by @yooniel31
    New Auto-Interp
    Negative Logits
     электрон
    0.45
    sburg
    0.45
     इलेक्ट्रॉनिक
    0.44
    ющих
    0.43
    ЕЛЬ
    0.43
    fæ
    0.42
    tà
    0.42
    abod
    0.42
    ஆன்
    0.42
    s
    0.41
    POSITIVE LOGITS
     assistant
    0.50
     Assistants
    0.48
     Assistant
    0.45
     assistants
    0.44
     asistente
    0.41
     Barb
    0.40
    志森
    0.40
     sociis
    0.40
    rot
    0.39
     Driven
    0.39
    Act Density 0.030%

    No Known Activations