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

    Neuronpedia

    INDEX
    Explanations

    run as administrator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    備
    0.43
     ciągu
    0.41
    缸
    0.39
    秒
    0.38
    ฟัง
    0.38
    ệ
    0.36
    த்திய
    0.36
     necks
    0.36
    ∶
    0.36
    桡
    0.35
    POSITIVE LOGITS
     run
    0.87
     Run
    0.84
    Run
    0.81
    run
    0.79
     running
    0.77
     administrator
    0.76
    Running
    0.72
     Running
    0.71
     Administrator
    0.71
     runs
    0.70
    Act Density 0.009%

    No Known Activations