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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     حرکت
    -0.07
     الحر
    -0.07
     died
    -0.06
     brakes
    -0.06
     handguns
    -0.06
    rok
    -0.06
    /u
    -0.06
    _HALF
    -0.06
     performers
    -0.06
    alignment
    -0.06
    POSITIVE LOGITS
    562
    0.06
     η
    0.06
    gan
    0.06
     useDispatch
    0.06
     tím
    0.06
    ENDING
    0.06
    ोद
    0.06
    opyright
    0.06
    astype
    0.06
    _SHA
    0.06
    Act Density 0.023%

    No Known Activations