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

    Neuronpedia

    INDEX
    Explanations

    two, pairs, linking two

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    余额
    0.41
     zowel
    0.40
     cả
    0.39
     ouvre
    0.39
    녔
    0.39
     সমষ্টি
    0.38
    ijdens
    0.38
     BOTH
    0.38
     ورځې
    0.37
    र्चे
    0.37
    POSITIVE LOGITS
     two
    1.36
    two
    1.24
    两个
    1.19
     pairs
    1.17
    同士
    1.13
     दोन
    1.11
    兩個
    1.09
     два
    1.08
     दो
    1.05
     două
    1.02
    Act Density 0.144%

    No Known Activations