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

    Neuronpedia

    INDEX
    Explanations

    To summarize/test/be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     borrow
    0.50
     borrowed
    0.48
     borrowing
    0.45
    Borrow
    0.42
     imp
    0.41
    멸
    0.39
     hé
    0.39
    borrow
    0.37
    我会
    0.37
    年前
    0.37
    POSITIVE LOGITS
     summarize
    0.89
     summarise
    0.86
    summar
    0.80
     summarizes
    0.79
     Summar
    0.71
     summarised
    0.71
    Summar
    0.71
    总结
    0.71
    summary
    0.71
     summary
    0.71
    Act Density 0.004%

    No Known Activations