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

    Neuronpedia

    INDEX
    Explanations

    posts, comments, and replies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sqlType
    0.75
     안내
    0.74
    rman
    0.69
    રણ
    0.69
    賦
    0.67
     पैकिंग
    0.67
     szí
    0.67
     MSCI
    0.66
     salesman
    0.66
    olina
    0.66
    POSITIVE LOGITS
     posts
    1.74
     Posts
    1.63
    Posts
    1.57
    投稿
    1.52
     comments
    1.50
    posts
    1.45
     Comments
    1.43
    Comments
    1.40
     posting
    1.40
    Replies
    1.39
    Act Density 0.339%

    No Known Activations