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

    Neuronpedia

    INDEX
    Explanations

    Russia

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _In
    -0.07
    	col
    -0.07
     �
    -0.06
    014
    -0.06
     Marie
    -0.06
     exhibition
    -0.06
     dining
    -0.06
    727
    -0.06
    ior
    -0.06
     RowBox
    -0.06
    POSITIVE LOGITS
     Russia
    0.11
     Russ
    0.10
     Russell
    0.10
     Russo
    0.09
     Russian
    0.09
    Russ
    0.08
     Russians
    0.08
     Putin
    0.08
    Russia
    0.08
    Russian
    0.07
    Act Density 0.028%

    No Known Activations