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

    Neuronpedia

    INDEX
    Explanations

    nationalities and their occupations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    language
    1.00
     language
    0.90
    地区
    0.87
     росій
    0.77
     شریف
    0.76
    drama
    0.76
    Russian
    0.75
     languages
    0.75
    scaping
    0.75
    地区的
    0.74
    POSITIVE LOGITS
    ಟ
    0.77
    वंश
    0.75
    eem
    0.74
     strut
    0.73
     inroads
    0.73
     зу
    0.73
    ट्यूब
    0.72
    esha
    0.70
     tenure
    0.70
     chemists
    0.70
    Act Density 0.055%

    No Known Activations