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

    Neuronpedia

    INDEX
    Explanations

    across the country

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Countries
    0.97
     countries
    0.96
     کشورهای
    0.93
    countries
    0.92
     देशों
    0.89
    Countries
    0.84
     worldwide
    0.79
     continent
    0.79
     Europe
    0.74
     Worldwide
    0.73
    POSITIVE LOGITS
    нное
    0.38
     함께
    0.38
    PERTIES
    0.37
    Ὁ
    0.36
     całym
    0.35
    ческому
    0.34
     pilotos
    0.34
     весь
    0.34
    intero
    0.34
    чним
    0.34
    Act Density 0.008%

    No Known Activations