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

    Neuronpedia

    INDEX
    Explanations

    city and region locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     woes
    0.42
     airline
    0.41
     airlines
    0.41
     mercantile
    0.41
     oppression
    0.39
     hysteria
    0.39
     manoeuv
    0.39
     was
    0.39
     免
    0.39
     törté
    0.38
    POSITIVE LOGITS
    Specifically
    0.51
    地区的
    0.50
    residents
    0.49
     регионе
    0.49
    地区
    0.48
     Specifically
    0.48
    地區
    0.48
    居民
    0.47
     bölges
    0.46
    region
    0.46
    Act Density 0.002%

    No Known Activations