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

    Neuronpedia

    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سیاسی
    0.47
    经营
    0.46
    政治
    0.45
     международ
    0.45
     specialising
    0.45
    political
    0.43
     politiques
    0.43
    商业
    0.43
     professionnel
    0.43
     ಕೆಲಸ
    0.43
    POSITIVE LOGITS
    8
    0.65
    4
    0.61
     that
    0.56
     two
    0.54
     data
    0.54
     list
    0.54
     eight
    0.53
     dataset
    0.53
    6
    0.53
     flavor
    0.53
    Act Density 0.007%

    No Known Activations