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

    Neuronpedia

    INDEX
    Explanations

    Material names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ذر
    -0.07
    _DISABLED
    -0.07
    _READY
    -0.06
    rebbe
    -0.06
    .BLACK
    -0.06
    俺は
    -0.06
    East
    -0.06
    .LogError
    -0.06
     supplements
    -0.06
     ders
    -0.06
    POSITIVE LOGITS
     Among
    0.07
     Hague
    0.06
     stuff
    0.06
     Bear
    0.06
     exit
    0.06
     compassionate
    0.06
     вибор
    0.06
     соврем
    0.06
    茂
    0.06
    �다
    0.06
    Act Density 0.002%

    No Known Activations