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

    Neuronpedia

    INDEX
    Explanations

    transport

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    魯
    -0.07
     Goku
    -0.06
    레스
    -0.06
     Freak
    -0.06
     tự
    -0.06
     Bolton
    -0.06
     classrooms
    -0.06
    visa
    -0.06
     JDK
    -0.06
    ائية
    -0.06
    POSITIVE LOGITS
    해서
    0.07
     arriving
    0.07
     ayant
    0.07
     nije
    0.07
     Present
    0.07
    !:
    0.07
    documento
    0.06
    uspended
    0.06
     Этот
    0.06
    _three
    0.06
    Act Density 0.015%

    No Known Activations