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

    Neuronpedia

    INDEX
    Explanations

    аж

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parsers
    -0.07
     coordinator
    -0.06
    服
    -0.06
    ModelAttribute
    -0.06
     Nullable
    -0.06
     Alta
    -0.06
    025
    -0.06
     عليها
    -0.06
     Tri
    -0.06
     DataManager
    -0.06
    POSITIVE LOGITS
    .TYPE
    0.07
     america
    0.07
    (tbl
    0.07
     أكتوبر
    0.06
     способ
    0.06
     arkadaş
    0.06
    发送
    0.06
     decrypted
    0.06
    LOB
    0.06
    lerce
    0.06
    Act Density 0.081%

    No Known Activations