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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sal
    -0.07
    ブリ
    -0.07
    ovaného
    -0.07
     ص
    -0.06
    běh
    -0.06
     على
    -0.06
    niční
    -0.06
     completely
    -0.06
    .ObjectModel
    -0.06
     Compatibility
    -0.06
    POSITIVE LOGITS
     class
    0.08
    class
    0.08
    -Class
    0.07
    �
    0.07
     YOUR
    0.06
     esteem
    0.06
     Subjects
    0.06
     inferior
    0.06
     Hammond
    0.06
     Confirmation
    0.06
    Act Density 0.002%

    No Known Activations