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

    Neuronpedia

    INDEX
    Explanations

    key explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Westchester
    1.03
     Southwest
    0.97
    Toronto
    0.94
     Toronto
    0.91
     Houston
    0.89
    埼玉
    0.87
    Maryland
    0.86
    纽约
    0.85
    Brooklyn
    0.85
     Maryland
    0.83
    POSITIVE LOGITS
     Ales
    0.67
    Flag
    0.67
     peer
    0.66
    versing
    0.65
     Baud
    0.65
     हड्ड
    0.65
     ke
    0.64
     Schell
    0.64
    FLAG
    0.64
     Kind
    0.63
    Act Density 0.042%

    No Known Activations