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

    Neuronpedia

    INDEX
    Explanations

    writing files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    詁
    0.46
    閱讀
    0.43
    読んで
    0.43
    dagog
    0.39
    阅读
    0.39
     Imported
    0.38
     лест
    0.37
     readings
    0.36
     নিদর্শন
    0.36
     đãi
    0.36
    POSITIVE LOGITS
     write
    2.08
     writing
    2.03
    写入
    2.03
     Write
    1.89
     writes
    1.88
     Writing
    1.87
    write
    1.83
    Write
    1.81
     WRITE
    1.73
     Writes
    1.71
    Act Density 0.072%

    No Known Activations