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

    Neuronpedia

    INDEX
    Explanations

    Mexico

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ل
    -0.08
     ISS
    -0.07
    ll
    -0.06
     Dys
    -0.06
     Strand
    -0.06
     гру
    -0.06
    112
    -0.06
     наруш
    -0.06
    _sub
    -0.06
    107
    -0.06
    POSITIVE LOGITS
     Mexican
    0.10
    Mex
    0.07
     Mexico
    0.07
    amazon
    0.07
     Decor
    0.07
     Mexicans
    0.07
     conqu
    0.06
    abic
    0.06
    vik
    0.06
     México
    0.06
    Act Density 0.009%

    No Known Activations