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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence agencies and classified operations

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

    intelligence, classified, budgets, operations, CIA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.57
    <()>
    -0.49
     Nab
    -0.47
    GOTREF
    -0.47
     Administrativna
    -0.47
     surla
    -0.46
     Bubble
    -0.44
     dàng
    -0.44
     nahilalakip
    -0.44
    migrationBuilder
    -0.44
    POSITIVE LOGITS
     برانيه
    0.54
     šķ
    0.50
     Geheim
    0.47
    lassified
    0.44
    classified
    0.43
    RenderAtEndOf
    0.42
     CIA
    0.41
    IntoConstraints
    0.41
     clandestine
    0.40
    rétaire
    0.40
    Act Density 0.226%

    No Known Activations