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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     సమస్య
    0.31
    बताया
    0.31
    ังหวัด
    0.30
    <unused2138>
    0.30
     dlatego
    0.30
     ሁኔታ
    0.30
    誡
    0.30
     داله
    0.29
     Sebab
    0.29
    Preferences
    0.28
    POSITIVE LOGITS
     L
    0.43
     United
    0.40
     Multi
    0.39
     H
    0.38
     C
    0.38
     U
    0.38
     M
    0.38
     P
    0.38
     S
    0.38
     D
    0.37
    Act Density 0.166%

    No Known Activations