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

    Neuronpedia

    INDEX
    Explanations

    place names endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nürnberg
    0.36
     Darmstadt
    0.34
    名古屋
    0.34
     Københav
    0.34
     Guangzhou
    0.34
     şekilde
    0.33
     Augsburg
    0.33
     Dortmund
    0.33
     Yokohama
    0.33
     Köln
    0.32
    POSITIVE LOGITS
    Village
    0.46
     village
    0.45
     Village
    0.42
     town
    0.38
     Belediyesi
    0.37
    村
    0.37
    Town
    0.36
     Manor
    0.36
     township
    0.34
    町
    0.34
    Act Density 0.020%

    No Known Activations