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

    Neuronpedia

    INDEX
    Explanations

    in, timeframes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CCCCCC
    -0.07
     zor
    -0.06
    ocuk
    -0.06
    途
    -0.06
    	de
    -0.06
    _slices
    -0.06
    dup
    -0.06
    ocos
    -0.06
    	dd
    -0.06
    lices
    -0.06
    POSITIVE LOGITS
    ồ
    0.07
    ่านมา
    0.06
    abi
    0.06
    ==$
    0.06
     três
    0.06
    .Migrations
    0.06
    ма
    0.06
     вне
    0.06
     Map
    0.06
    ！！
    0.06
    Act Density 0.104%

    No Known Activations