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

    Neuronpedia

    INDEX
    Explanations

    regions and cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     부산
    0.89
    부산
    0.85
    高雄
    0.80
    福岡
    0.74
     जोधपुर
    0.69
     Busan
    0.67
     İzmir
    0.56
     Fukuoka
    0.56
     চট্টগ্রাম
    0.55
    熊本
    0.54
    POSITIVE LOGITS
    栃木
    0.84
     Hertfordshire
    0.72
    埼玉県
    0.66
    경기도
    0.63
     हरियाणा
    0.62
    埼玉
    0.59
    関東
    0.59
     मेरठ
    0.55
     ময়মনসিংহ
    0.55
    日光
    0.55
    Act Density 0.010%

    No Known Activations