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

    Neuronpedia

    INDEX
    Explanations

    dirname

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    屑
    -0.07
     recap
    -0.07
    論
    -0.07
     fileName
    -0.07
    哂
    -0.07
     că
    -0.07
     있을
    -0.07
    机器人
    -0.06
     Рас
    -0.06
     Resize
    -0.06
    POSITIVE LOGITS
     flavored
    0.09
    向记者
    0.08
     �
    0.07
    옮
    0.07
     ايضا
    0.07
    �
    0.07
    是一個
    0.07
     Directed
    0.07
    (high
    0.07
    可通过
    0.07
    Act Density 0.001%

    No Known Activations