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

    Neuronpedia

    INDEX
    Explanations

    references to armed groups and their activities in conflict contexts

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

    Conflict, unrest, or violence

    np_acts-logits-general · gemini-2.0-flash

    violence and conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.86
     supérieures
    -0.70
     bacio
    -0.65
     hoogte
    -0.63
    eynman
    -0.61
     embarazadas
    -0.58
     ExecuteAsync
    -0.57
     financières
    -0.57
    wiss
    -0.56
     enfans
    -0.55
    POSITIVE LOGITS
     violence
    1.26
     instability
    1.21
     conflict
    1.15
     violent
    1.09
     security
    1.05
     insecurity
    1.05
     stability
    1.05
     peace
    1.02
     unrest
    1.02
    Violence
    0.99
    Act Density 0.250%

    No Known Activations