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

    Neuronpedia

    INDEX
    Explanations

    Language, environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lately
    -0.09
    %"),↵
    -0.09
     最近
    -0.08
    彩�
    -0.08
     ");↵↵
    -0.08
     ")↵
    -0.08
     kinda
    -0.08
     amel
    -0.08
     ")↵↵
    -0.08
    %");↵
    -0.08
    POSITIVE LOGITS
     полноцен
    0.09
    =n
    0.08
     alone
    0.08
     reguliere
    0.08
     рынок
    0.08
     обыч
    0.08
    +n
    0.08
     regular
    0.07
     же
    0.07
    -alone
    0.07
    Act Density 0.352%

    No Known Activations