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

    Neuronpedia

    INDEX
    Explanations

    regions and administrative divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CANADA
    0.76
     spam
    0.73
     canadien
    0.71
     Cloning
    0.70
     Italien
    0.70
     GATT
    0.69
     nœ
    0.69
    Europe
    0.68
     Brownian
    0.67
     Deutschland
    0.67
    POSITIVE LOGITS
     districts
    1.77
     Kabupaten
    1.52
     Districts
    1.50
     provinces
    1.46
     northern
    1.45
     southern
    1.40
     province
    1.40
     regions
    1.39
     kabupaten
    1.39
     district
    1.36
    Act Density 0.148%

    No Known Activations