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

    Neuronpedia

    INDEX
    Explanations

    overwhelmed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     histoire
    -0.07
    ran
    -0.06
    adors
    -0.06
     açı
    -0.06
     IList
    -0.06
    �
    -0.06
    ��
    -0.06
     UserModel
    -0.06
     Garten
    -0.06
    rost
    -0.06
    POSITIVE LOGITS
    Bitcoin
    0.07
     incentiv
    0.07
    submission
    0.06
    (addr
    0.06
    observation
    0.06
    artifact
    0.06
     PUSH
    0.06
     backpack
    0.06
     RemoteException
    0.06
     Columbus
    0.06
    Act Density 0.019%

    No Known Activations