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

    Neuronpedia

    INDEX
    Explanations

    posting content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Với
    0.66
    Kết
    0.62
    𝘿
    0.60
    Apakah
    0.60
    酪
    0.59
    聝
    0.59
    他们的
    0.58
    एक्स
    0.57
    Từ
    0.57
     Ді
    0.57
    POSITIVE LOGITS
     posting
    0.98
     uploads
    0.84
     posted
    0.83
     upload
    0.83
     Posting
    0.80
     posts
    0.79
     uploading
    0.78
     postings
    0.78
     shortly
    0.76
     blog
    0.75
    Act Density 0.005%

    No Known Activations