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

    Neuronpedia

    INDEX
    Explanations

    name matching understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     نمونه
    0.43
    මාණය
    0.39
     為
    0.39
    0.38
     ประมาณ
    0.38
     중앙
    0.38
    Kost
    0.38
    vação
    0.37
    ஞான
    0.37
     kỷ
    0.37
    POSITIVE LOGITS
     форум
    0.43
    ORN
    0.42
    without
    0.42
    carbox
    0.41
     how
    0.41
     born
    0.41
     without
    0.40
    mp
    0.40
     ইউনিভার্সিটি
    0.40
     Sp
    0.39
    Act Density 0.000%

    No Known Activations