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

    Neuronpedia

    INDEX
    Explanations

    Canada

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     American
    0.85
    American
    0.83
     अमेर
    0.83
     AMERICAN
    0.82
    AMERICAN
    0.79
     আমেরিকান
    0.78
    أم
    0.78
     uplift
    0.77
     Ameri
    0.76
     американ
    0.75
    POSITIVE LOGITS
     Canada
    1.25
    Canada
    1.24
     Quebec
    1.14
     Manitoba
    1.12
     Canadian
    1.11
     canada
    1.11
     Canadá
    1.11
     RCMP
    1.09
     Canadians
    1.07
     Winnipeg
    1.05
    Act Density 0.047%

    No Known Activations