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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giữ
    -0.07
    package
    -0.07
    باقي
    -0.07
     Dave
    -0.06
    治愈
    -0.06
    �
    -0.06
    肌肉
    -0.06
    	users
    -0.06
    创造了
    -0.06
    (card
    -0.06
    POSITIVE LOGITS
    .txt
    0.07
    魂
    0.07
    ระบ
    0.07
     khả
    0.07
    拨
    0.07
    -calendar
    0.06
     voters
    0.06
     warfare
    0.06
    -selection
    0.06
    ISHED
    0.06
    Act Density 0.021%

    No Known Activations