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

    Neuronpedia

    INDEX
    Explanations

    references to wars and military actions

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

    waged war or campaign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lewati
    -0.42
    Disable
    -0.41
     dismissing
    -0.41
    -------------</
    -0.40
     Süß
    -0.39
     réservation
    -0.39
    izador
    -0.39
     확인함
    -0.39
    unque
    -0.39
    DISABLE
    -0.39
    POSITIVE LOGITS
     war
    0.58
     warfare
    0.57
     Jihad
    0.56
     waged
    0.52
     Crusade
    0.49
     strijd
    0.47
     crusade
    0.46
     wars
    0.46
    \{\\
    0.45
     campaign
    0.44
    Act Density 0.069%

    No Known Activations