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

    Neuronpedia

    INDEX
    Explanations

    Canadian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canadians
    -2.08
     Canadian
    -1.99
     Canada
    -1.98
     CANADA
    -1.92
    Canada
    -1.91
    Canadian
    -1.87
    canadian
    -1.77
     CANADIAN
    -1.77
    CANADA
    -1.70
     canada
    -1.70
    POSITIVE LOGITS
    ian
    0.44
    vi
    0.41
    ’
    0.41
    ry
    0.40
     estan
    0.39
    .
    0.38
    '
    0.36
    AA
    0.36
                                   
    0.36
     Chi
    0.35
    Act Density 0.202%

    No Known Activations