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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    투
    -0.08
     {!
    -0.07
    _PUSH
    -0.07
     Del
    -0.07
     常
    -0.07
     Issues
    -0.06
    etically
    -0.06
    Nearly
    -0.06
     hủy
    -0.06
     Cook
    -0.06
    POSITIVE LOGITS
     tủ
    0.07
    ~↵↵
    0.07
    ichtig
    0.06
    ‌انبار
    0.06
     مخروط
    0.06
    appa
    0.06
    UDP
    0.06
    ettel
    0.06
    .MouseEventHandler
    0.06
    _calendar
    0.06
    Act Density 0.014%

    No Known Activations