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

    Neuronpedia

    INDEX
    Explanations

    Professions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    219
    -0.07
    99
    -0.07
     recursion
    -0.07
    598
    -0.07
    _case
    -0.07
    490
    -0.06
    ool
    -0.06
    喝
    -0.06
     rob
    -0.06
    898
    -0.06
    POSITIVE LOGITS
     physician
    0.11
     Physician
    0.10
     physicians
    0.10
     Physicians
    0.09
     privat
    0.08
     styled
    0.07
    пион
    0.07
    IN
    0.07
    ian
    0.07
    <div
    0.07
    Act Density 0.004%

    No Known Activations