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

    Neuronpedia

    INDEX
    Explanations

    learning and evolving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aboriginal
    0.49
     in
    0.48
     authentic
    0.46
     the
    0.46
     lakhs
    0.46
     aboriginal
    0.46
     agricult
    0.45
     alarming
    0.45
     deletion
    0.45
     only
    0.45
    POSITIVE LOGITS
     Chương
    0.47
     cùng
    0.46
     điều
    0.46
     mấy
    0.46
     bảo
    0.45
    OS
    0.44
     dịch
    0.44
     chương
    0.43
     tự
    0.43
    Điều
    0.43
    Act Density 0.006%

    No Known Activations