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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    岂
    -0.07
     �
    -0.07
     doivent
    -0.07
    房东
    -0.07
    still
    -0.07
     �
    -0.07
    噤
    -0.07
     لي
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Db
    0.08
    经验和
    0.08
    组合
    0.07
     XmlDocument
    0.07
    ActionButton
    0.07
     singers
    0.07
     talented
    0.07
    魔王
    0.07
    (actions
    0.07
    롼
    0.06
    Act Density 0.042%

    No Known Activations