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

    Neuronpedia

    INDEX
    Explanations

    run code or script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    maintenance
    0.63
    log
    0.63
    চ্ছন্ন
    0.61
    的代码
    0.61
    ፊ
    0.59
     declar
    0.59
     club
    0.57
    鋒
    0.57
     नर्सिंग
    0.57
    vim
    0.57
    POSITIVE LOGITS
     Run
    0.91
     Running
    0.88
     run
    0.84
    Run
    0.82
    Running
    0.82
     Runs
    0.80
    runs
    0.79
     runs
    0.79
     chạy
    0.77
     running
    0.77
    Act Density 0.066%

    No Known Activations