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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    收纳
    -0.08
    核查
    -0.08
    貝
    -0.08
    /se
    -0.08
    	product
    -0.07
    _lens
    -0.07
    _sz
    -0.07
     singles
    -0.07
     strikeouts
    -0.07
     sucks
    -0.07
    POSITIVE LOGITS
     ______
    0.07
    延迟
    0.07
    毁
    0.07
     Yelp
    0.07
    .Remote
    0.07
    0.07
    0.07
     Estates
    0.06
    交替
    0.06
     \\
    0.06
    Act Density 0.006%

    No Known Activations