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

    Neuronpedia

    INDEX
    Explanations

    city names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Angel
    0.42
     Alpha
    0.40
     humankind
    0.40
    在中国
    0.38
     MOR
    0.38
     alph
    0.38
    ÂN
    0.38
     GEORGE
    0.38
    ','$
    0.38
    '>"
    0.38
    POSITIVE LOGITS
     부산
    1.62
    仙台
    1.54
     제주
    1.52
    부산
    1.48
     চট্টগ্রাম
    1.39
     Surabaya
    1.39
    静岡
    1.38
    福岡
    1.34
     রাজশাহী
    1.33
     চট্টগ্রামের
    1.32
    Act Density 0.041%

    No Known Activations