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

    Neuronpedia

    INDEX
    Explanations

    regional variations and divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    村民
    0.80
     ಗ್ರಾಮ
    0.75
     villagers
    0.75
    ร้าน
    0.74
     restaurant
    0.70
    restaurant
    0.69
    village
    0.69
     empleados
    0.67
    Restaurant
    0.65
    ボタン
    0.64
    POSITIVE LOGITS
     region
    1.62
     regions
    1.58
    Regional
    1.57
    region
    1.55
     Regional
    1.55
     Region
    1.52
     regional
    1.52
     Regions
    1.51
    Region
    1.49
    Regions
    1.36
    Act Density 0.106%

    No Known Activations