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

    Neuronpedia

    INDEX
    Explanations

    little followed by title

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आगा
    0.44
    다는
    0.43
    이지만
    0.41
    Alton
    0.39
     Alton
    0.38
     ඒ
    0.38
    ább
    0.38
    డీపీ
    0.38
     ਉਨ੍ਹਾਂ
    0.38
     thoe
    0.38
    POSITIVE LOGITS
     Change
    0.37
     Shops
    0.37
    MEA
    0.36
     RE
    0.36
     Library
    0.36
     Yoga
    0.36
     pharetra
    0.36
    카페
    0.35
     running
    0.35
     DISC
    0.35
    Act Density 0.000%

    No Known Activations