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

    Neuronpedia

    INDEX
    Explanations

    new locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rồi
    0.61
     vegetables
    0.60
    廠商
    0.60
     tạp
    0.58
    杂
    0.58
    参数
    0.57
     anvä
    0.57
     Anbieter
    0.56
     protéines
    0.55
    一般
    0.54
    POSITIVE LOGITS
     locations
    1.72
     Locations
    1.65
    locations
    1.52
    Locations
    1.52
    各地
    1.31
     location
    1.27
     Location
    1.20
    location
    1.15
     campuses
    1.15
     wherever
    1.14
    Act Density 0.829%

    No Known Activations