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

    Neuronpedia

    INDEX
    Explanations

    tasks requiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    用于
    0.47
    用於
    0.45
     用于
    0.43
    สำหรับการ
    0.42
    ථා
    0.40
    សម្រាប់
    0.39
     برای
    0.38
    ສໍາ
    0.38
    για
    0.38
     для
    0.37
    POSITIVE LOGITS
     requiring
    1.32
     nécess
    1.10
     involving
    1.02
     memerlukan
    1.02
     requires
    1.00
     require
    1.00
     wymag
    0.95
     membutuhkan
    0.94
    require
    0.92
     требу
    0.91
    Act Density 0.020%

    No Known Activations