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

    Neuronpedia

    INDEX
    Explanations

    XML code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Position
    -0.08
    ﳌ
    -0.07
     ENV
    -0.07
     {|
    -0.07
    萬元
    -0.07
    monitor
    -0.07
     Won
    -0.06
     Traverse
    -0.06
     solution
    -0.06
     Dense
    -0.06
    POSITIVE LOGITS
    展示
    0.08
    ------------------------------------------------------------------------------------------------
    0.07
    礼仪
    0.07
    ，
    0.07
    	camera
    0.07
    姑
    0.07
    夫妻
    0.07
    ：
    0.07
    、
    0.07
    `.
    0.07
    Act Density 0.000%

    No Known Activations