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

    Neuronpedia

    INDEX
    Explanations

    with open as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeValue
    0.46
     Write
    0.46
     write
    0.43
     loading
    0.41
    Write
    0.40
    write
    0.40
     Reload
    0.40
    写
    0.40
    写入
    0.38
    CellValue
    0.38
    POSITIVE LOGITS
     opened
    1.03
     handle
    1.00
    opened
    0.99
    handle
    0.96
     откры
    0.91
    打开
    0.88
     Opened
    0.87
     otev
    0.86
     öpp
    0.86
     відкри
    0.85
    Act Density 0.027%

    No Known Activations