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

    Neuronpedia

    INDEX
    Explanations

    World War II

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commuters
    -0.09
     pencil
    -0.08
     pencils
    -0.08
     Parking
    -0.08
     Pencil
    -0.08
    mouseleave
    -0.08
     Spine
    -0.07
    (step
    -0.07
    (limit
    -0.07
     creamy
    -0.07
    POSITIVE LOGITS
     Allies
    0.14
     Allied
    0.12
     الحرب
    0.12
     savaş
    0.11
     allies
    0.11
     युद्ध
    0.11
     যুদ্ধ
    0.11
    enemy
    0.11
     союз
    0.11
     allied
    0.10
    Act Density 0.035%

    No Known Activations