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

    Neuronpedia

    INDEX
    Explanations

    html meta content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    γέν
    0.44
     menyimpan
    0.41
     speichern
    0.41
     Utara
    0.40
    ␥
    0.39
     trái
    0.39
    下游
    0.39
    ﮩ
    0.39
    যাত্রা
    0.39
     titre
    0.39
    POSITIVE LOGITS
     content
    0.80
    content
    0.72
     CONTENT
    0.63
     Content
    0.62
    Content
    0.61
     contents
    0.52
    内容
    0.52
    CONTENT
    0.50
     कंटेंट
    0.49
    的内容
    0.47
    Act Density 0.006%

    No Known Activations