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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alike
    -0.08
     Fixed
    -0.07
    EntryPoint
    -0.07
    الف
    -0.06
     효
    -0.06
     apart
    -0.06
     *,↵
    -0.06
     inspect
    -0.06
     znám
    -0.06
     traced
    -0.06
    POSITIVE LOGITS
    .should
    0.13
    should
    0.11
    _should
    0.09
    .Should
    0.08
    must
    0.07
     Should
    0.07
     should
    0.07
     mandatory
    0.07
    (FLAGS
    0.07
     الولايات
    0.07
    Act Density 0.006%

    No Known Activations