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

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     timer
    -0.07
    _gid
    -0.06
    ocation
    -0.06
    focus
    -0.06
    pth
    -0.06
     hurried
    -0.06
     ظرفیت
    -0.06
    Times
    -0.06
    inary
    -0.06
     coded
    -0.06
    POSITIVE LOGITS
     一般
    0.07
    ди
    0.07
     �
    0.07
    Wake
    0.07
    我們
    0.06
     आप
    0.06
    CLUDING
    0.06
    don
    0.06
    PLAIN
    0.06
     Viet
    0.06
    Act Density 0.007%

    No Known Activations