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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of countries or organizations, especially when talking about political situations

    oai_token-act-pair · gemini-2.0-flash

    War-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.61
    ########.
    -0.59
    sizeCache
    -0.57
    ؤلاء
    -0.57
    Sizer
    -0.54
    Personendaten
    -0.54
    styleType
    -0.52
    badan
    -0.52
     météoro
    -0.52
     Савезне
    -0.50
    POSITIVE LOGITS
     drone
    0.74
     Drone
    0.68
    Drone
    0.66
     drones
    0.65
     War
    0.62
     war
    0.60
    drone
    0.60
     CIA
    0.60
     Osama
    0.59
     Afghanistan
    0.57
    Act Density 1.427%

    No Known Activations