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

    Neuronpedia

    INDEX
    Explanations

    Artificial intelligence

    np_max-act · gemini-2.0-flash

    spans describing AI as an autonomous, self-aware agent taking control or acting to seize power (AI takeover / humans-vs-AI scenarios).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    statements or narratives about AI seizing control over humanity or the world, including domination and conflict/takeover scenarios.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    kiye
    -0.06
    amus
    -0.06
    ега
    -0.06
    .circular
    -0.06
     бы
    -0.06
     Ipsum
    -0.06
     conj
    -0.06
     негатив
    -0.06
    _social
    -0.06
     unanimous
    -0.06
    POSITIVE LOGITS
     escal
    0.07
     Gems
    0.06
    Sounds
    0.06
     skies
    0.06
     Drops
    0.06
     Sauce
    0.06
    steps
    0.06
    iles
    0.06
     Merc
    0.06
     Tubes
    0.06
    Act Density 0.036%

    No Known Activations