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

    Neuronpedia

    INDEX
    Explanations

    words related to dangerous or harmful substances and traps

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

    dangerous environmental hazards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.41
     visuales
    -0.39
     potřeb
    -0.38
    wieś
    -0.38
     capacità
    -0.36
     linearity
    -0.36
    initializeApp
    -0.35
    enschap
    -0.35
     ajutor
    -0.35
     behaupten
    -0.35
    POSITIVE LOGITS
     traps
    0.73
    poison
    0.64
     trap
    0.64
    enderror
    0.62
     poison
    0.61
     المعيارى
    0.61
     hazards
    0.60
     hazard
    0.59
     poisonous
    0.58
    Poison
    0.58
    Act Density 0.021%

    No Known Activations