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

    Neuronpedia

    INDEX
    Explanations

    start, end, and sum calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     барои
    0.44
     जिसके
    0.38
     соблю
    0.38
     möglichen
    0.38
     අවශ්‍ය
    0.38
     செயல்பா
    0.37
     рекомендации
    0.37
    izzando
    0.37
     പ്രതീക്ഷ
    0.36
     ఆలో
    0.36
    POSITIVE LOGITS
    ↵
    0.44
    ↵↵
    0.44
    8
    0.38
    <start_of_image>
    0.37
     more
    0.36
     C
    0.35
    /
    0.35
    9
    0.35
     K
    0.34
    6
    0.34
    Act Density 0.250%

    No Known Activations