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

    Neuronpedia

    INDEX
    Explanations

    York

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ρίζ
    -0.07
    _Att
    -0.07
     Rel
    -0.06
    φερ
    -0.06
     tří
    -0.06
    전
    -0.06
    .Cont
    -0.06
    _SUPER
    -0.06
     Fle
    -0.06
     Twe
    -0.06
    POSITIVE LOGITS
     York
    0.18
    York
    0.11
     NY
    0.11
     york
    0.11
     YORK
    0.10
    yny
    0.09
     Yorker
    0.09
    NY
    0.08
     Ny
    0.08
    London
    0.08
    Act Density 0.012%

    No Known Activations