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

    Neuronpedia

    INDEX
    Explanations

    India and Indian entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഇമാം
    0.83
     தமிழரசுக்
    0.83
     দিবে
    0.80
     বাসার
    0.79
     লাশ
    0.78
     Wyoming
    0.76
     পানি
    0.75
     নেতাকর্ম
    0.75
     Greensboro
    0.74
    初
    0.74
    POSITIVE LOGITS
     India
    1.90
     Indian
    1.86
    India
    1.84
    Indian
    1.75
    印度
    1.66
    ₹
    1.66
     india
    1.64
     Indians
    1.58
     indian
    1.56
     ₹
    1.55
    Act Density 0.133%

    No Known Activations