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

    Neuronpedia

    INDEX
    Explanations

    instant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ));↵↵
    -0.07
    xffff
    -0.07
     dims
    -0.07
    Datas
    -0.07
     drill
    -0.06
    錯誤
    -0.06
    -bedroom
    -0.06
    ';
    -0.06
    _topics
    -0.06
    既
    -0.06
    POSITIVE LOGITS
     exponential
    0.07
     linguistic
    0.07
    stant
    0.07
    鹀
    0.07
    昊
    0.07
     interpreted
    0.07
    sto
    0.07
     ela
    0.07
     перевод
    0.07
    	not
    0.07
    Act Density 0.005%

    No Known Activations