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

    Neuronpedia

    INDEX
    Explanations

    references to global events and organizations, particularly related to health and warfare

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

    "World" followed by "Health" or "War."

    np_acts-logits-general · gemini-2.0-flash

    World Health, World War

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hauptartikel
    -0.75
    ValueStyle
    -0.68
    SourceChecksum
    -0.66
    cshtml
    -0.62
    verwijspagina
    -0.61
    曖昧さ回避
    -0.60
    ConstraintMaker
    -0.56
    expandindo
    -0.54
    WSGI
    -0.51
     linkovi
    -0.50
    POSITIVE LOGITS
     War
    0.58
     Famous
    0.57
     bank
    0.57
    FormState
    0.56
     class
    0.56
     famous
    0.55
     Bank
    0.54
    >--}}
    0.53
     renowned
    0.53
    Famous
    0.52
    Act Density 0.079%

    No Known Activations