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

    Neuronpedia

    INDEX
    Explanations

    lmsys.org blog posts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revest
    0.51
    قاء
    0.44
     />);
    0.44
     Staffordshire
    0.44
     sile
    0.43
     ഉപയോഗ
    0.42
     Prepaid
    0.42
    嫚
    0.42
    唒
    0.42
    payroll
    0.41
    POSITIVE LOGITS
    arXiv
    0.80
     arXiv
    0.80
     OpenAI
    0.80
     AI
    0.78
     hugging
    0.77
    论文
    0.75
     gradio
    0.74
     arxiv
    0.73
     Hug
    0.72
    arxiv
    0.72
    Act Density 0.052%

    No Known Activations