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

    Neuronpedia

    INDEX
    Explanations

    terms related to weapons and lethal technologies

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

    lethal weapons destruction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ujednoznacz
    -0.64
    BagLayout
    -0.53
     nakalista
    -0.52
     ControllerBase
    -0.45
     FetchType
    -0.44
    ficulties
    -0.44
    surate
    -0.42
    ագր
    -0.41
    livia
    -0.41
    homonymie
    -0.41
    POSITIVE LOGITS
     weapon
    0.81
    weapon
    0.79
     lethal
    0.73
     deadly
    0.69
    weapons
    0.66
    Weapon
    0.66
     weapons
    0.65
     deadliest
    0.62
     Weapon
    0.62
    WEAPON
    0.60
    Act Density 0.104%

    No Known Activations