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

    Neuronpedia

    INDEX
    Explanations

    MERCHANTABILITY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fur
    -0.07
     Nam
    -0.07
    首发
    -0.07
    头部
    -0.07
     ebony
    -0.07
    ธนา
    -0.07
     commercial
    -0.07
    开工建设
    -0.07
     warned
    -0.07
    引入
    -0.07
    POSITIVE LOGITS
     synergy
    0.08
    (schema
    0.07
     figured
    0.07
    主义思想
    0.07
     отлично
    0.07
     sulph
    0.07
    ящих
    0.07
    bins
    0.07
    	dfs
    0.07
    osas
    0.07
    Act Density 0.002%

    No Known Activations