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

    Neuronpedia

    INDEX
    Explanations

    terms related to explosives and detonators

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

    mines and ordnance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.41
     CallOverrides
    -0.41
    jewództ
    -0.40
    isContained
    -0.40
    tahankan
    -0.40
    capaian
    -0.36
     capuche
    -0.36
     capucha
    -0.36
    NOPQRST
    -0.35
    Companion
    -0.35
    POSITIVE LOGITS
     Infórmanos
    0.56
     civilian
    0.54
     safest
    0.53
     dangerous
    0.52
     civilians
    0.50
     Hazards
    0.49
     danger
    0.49
     dangers
    0.48
     military
    0.47
     militari
    0.47
    Act Density 0.004%

    No Known Activations