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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gan
    -0.07
     diesel
    -0.07
    _dot
    -0.06
     mile
    -0.06
    .scheme
    -0.06
    _DIM
    -0.06
     Cs
    -0.06
     breakdown
    -0.06
     external
    -0.06
     DAG
    -0.06
    POSITIVE LOGITS
     питання
    0.07
     вариант
    0.07
    Adv
    0.06
    ิทย
    0.06
    Navbar
    0.06
    اته
    0.06
     Brah
    0.06
     GRAT
    0.06
    诊
    0.06
    	BufferedReader
    0.06
    Act Density 0.048%

    No Known Activations