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

    Neuronpedia

    INDEX
    Explanations

    countries and nationalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تے
    0.70
    ê
    0.65
    cích
    0.64
    नं
    0.62
    ξε
    0.61
    ä
    0.61
    𝔬
    0.61
    έ
    0.60
    其他
    0.60
    댑
    0.60
    POSITIVE LOGITS
     Мекси
    1.20
     Mexican
    1.05
    Buenos
    1.05
     Oaxaca
    1.02
     Buenos
    1.01
    Mexico
    1.00
     अर्जेंटीना
    1.00
    Mexican
    1.00
     Uruguay
    0.99
     আর্জেন্টিনার
    0.98
    Act Density 0.342%

    No Known Activations