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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hữu
    -0.08
    ﮈ
    -0.07
    쎈
    -0.07
     BUSINESS
    -0.07
    瑰
    -0.06
     Bei
    -0.06
    莞
    -0.06
     ?>><?
    -0.06
    虬
    -0.06
     StObject
    -0.06
    POSITIVE LOGITS
    [temp
    0.07
     minds
    0.07
    届毕业生
    0.07
     wrong
    0.07
    ()->
    0.07
         
↵
    0.07
    istory
    0.07
    ↵		
↵
    0.07
    闪过
    0.07
    路过
    0.07
    Act Density 0.232%

    No Known Activations