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

    Neuronpedia

    INDEX
    Explanations

    settlers and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    容量
    0.54
    してください
    0.47
     নিয়েছে
    0.47
     বেশি
    0.47
     NASCAR
    0.47
    圣
    0.47
    礻
    0.47
     TVA
    0.46
     Amtrak
    0.46
    矢量
    0.46
    POSITIVE LOGITS
     Otago
    0.84
     Dunedin
    0.80
     Christchurch
    0.77
     Maori
    0.71
     Ballarat
    0.67
     verand
    0.66
     Canterbury
    0.65
     Auckland
    0.64
     railway
    0.64
     Wellington
    0.60
    Act Density 0.002%

    No Known Activations