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

    Neuronpedia

    INDEX
    Explanations

    York

    np_max-act · gemini-2.0-flash

    This neuron specifically activates on the token “York,” most notably when it appears as part of “New York.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tostring
    -0.07
    dda
    -0.06
     духов
    -0.06
     Init
    -0.06
    	Camera
    -0.06
    (f
    -0.06
     Girlfriend
    -0.06
     Afterwards
    -0.06
     fetus
    -0.06
    IER
    -0.06
    POSITIVE LOGITS
     York
    0.17
     YORK
    0.10
    York
    0.10
     Yorker
    0.10
     york
    0.09
     Yorkers
    0.08
     neurop
    0.08
     NY
    0.08
     are
    0.08
     Oregon
    0.07
    Act Density 0.012%

    No Known Activations