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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    られている
    -0.07
     realized
    -0.07
     Workbook
    -0.07
    .Results
    -0.06
    -</
    -0.06
    .'↵↵
    -0.06
     prescriptions
    -0.06
     prerequisites
    -0.06
     Csv
    -0.06
    9
    -0.06
    POSITIVE LOGITS
     releg
    0.08
    pherical
    0.06
    ･･
    0.06
    laces
    0.06
     madre
    0.06
    لات
    0.06
    �
    0.06
    尘
    0.06
    _BASIC
    0.06
     darn
    0.06
    Act Density 0.013%

    No Known Activations