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

    Neuronpedia

    INDEX
    Explanations

    places people live

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Publisher
    0.77
    engine
    0.75
     seller
    0.75
     продав
    0.74
    seller
    0.71
     Travels
    0.68
    номо
    0.67
    的路
    0.66
     кө
    0.66
    road
    0.66
    POSITIVE LOGITS
     dormitory
    1.92
     inmates
    1.79
     dorm
    1.62
     inmate
    1.60
     residents
    1.58
     hostel
    1.57
     detainees
    1.50
     시설
    1.46
    宿舍
    1.43
     Residents
    1.43
    Act Density 0.094%

    No Known Activations