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

    Neuronpedia

    INDEX
    Explanations

    writing to files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Formatting
    0.48
    坯
    0.41
     formatting
    0.39
    Formatting
    0.39
    FORMAT
    0.39
    formatting
    0.38
     stif
    0.37
    ACION
    0.37
    艰难
    0.37
     defibr
    0.37
    POSITIVE LOGITS
     write
    1.15
    write
    1.14
    Write
    1.08
     Write
    1.04
     writes
    1.04
    寫
    0.93
     wrote
    0.93
     Writes
    0.91
     пише
    0.89
     WRITE
    0.86
    Act Density 0.007%

    No Known Activations