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

    Neuronpedia

    INDEX
    Explanations

    United States/USA locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ronym
    0.41
     প্রবন্ধে
    0.41
    NHK
    0.40
    社の
    0.39
     senador
    0.39
    IOT
    0.39
    安倍
    0.38
    Safe
    0.38
    羞
    0.38
     JOptionPane
    0.37
    POSITIVE LOGITS
     United
    1.15
    United
    1.01
     USA
    0.98
     США
    0.91
    USA
    0.88
     Verenigde
    0.86
     UNITED
    0.83
     الولايات
    0.80
    UNITED
    0.80
     US
    0.77
    Act Density 0.007%

    No Known Activations