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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ney
    -0.07
    	Console
    -0.07
    “To
    -0.07
     Україн
    -0.06
     використовувати
    -0.06
    friendly
    -0.06
     Ром
    -0.06
     جذ
    -0.06
     annotated
    -0.06
    "To
    -0.06
    POSITIVE LOGITS
     erv
    0.07
    ốc
    0.07
     unp
    0.07
    族
    0.06
    _mex
    0.06
     lá
    0.06
    dings
    0.06
     likely
    0.06
     وح
    0.06
     Secretary
    0.06
    Act Density 0.028%

    No Known Activations