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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence operations and agencies

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

    intelligence and espionage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.50
    AutoScale
    -0.44
    prnewswire
    -0.42
     estekak
    -0.42
    migrationBuilder
    -0.41
    openzeppelin
    -0.40
    roned
    -0.38
     IconData
    -0.37
     UIApplication
    -0.37
    Bol
    -0.37
    POSITIVE LOGITS
     spy
    0.85
     espionage
    0.78
     spies
    0.74
     spion
    0.72
     spying
    0.68
     intelligence
    0.68
     Intelligence
    0.67
    Intelligence
    0.64
     Spy
    0.59
     surveillance
    0.57
    Act Density 0.205%

    No Known Activations