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

    Neuronpedia

    INDEX
    Explanations

    running

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝕟
    0.36
    éraires
    0.35
    ত্যা
    0.35
    न्छ
    0.34
    ഗ
    0.32
    ফের
    0.31
    chow
    0.31
     поса
    0.31
    ισε
    0.31
    arez
    0.31
    POSITIVE LOGITS
     running
    3.83
     Running
    3.56
    Running
    3.48
    running
    3.38
     chạy
    2.34
    运行
    2.16
    isRunning
    1.88
    วิ่ง
    1.79
    運行
    1.66
    跑
    1.65
    Act Density 0.004%

    No Known Activations