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

    Neuronpedia

    INDEX
    Explanations

    The United States

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AMERICAN
    0.62
    AMERICAN
    0.60
    American
    0.60
    群众
    0.57
     overly
    0.57
     otherwise
    0.56
    Call
    0.56
    otherwise
    0.55
    Similarly
    0.55
     محیط
    0.54
    POSITIVE LOGITS
     United
    2.24
    United
    2.05
     UNITED
    1.56
    UNITED
    1.46
     UK
    1.42
     यूनाइटेड
    1.37
    united
    1.31
     U
    1.30
     Vereinigten
    1.30
     Unite
    1.28
    Act Density 0.072%

    No Known Activations