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

    Neuronpedia

    INDEX
    Explanations

    historical figures and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PCOS
    0.81
    导弹
    0.80
     multicultural
    0.79
    NATO
    0.79
     medieval
    0.78
     Falcon
    0.78
     Segal
    0.77
     plenum
    0.76
     falcon
    0.76
    渔
    0.75
    POSITIVE LOGITS
     Railway
    1.04
     Railroad
    1.02
     १८४
    1.01
     railway
    1.01
     railways
    0.98
     railroad
    0.97
     railroads
    0.95
     ১৮
    0.91
     Napoleon
    0.90
     १८
    0.89
    Act Density 0.291%

    No Known Activations