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

    Neuronpedia

    INDEX
    Explanations

    quiz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resonate
    -0.07
     carry
    -0.07
     collaborate
    -0.07
     palabra
    -0.06
     Stanley
    -0.06
     TODAY
    -0.06
     상세
    -0.06
     Momentum
    -0.06
     lesb
    -0.06
    ्यकत
    -0.06
    POSITIVE LOGITS
     quizzes
    0.08
     quiz
    0.08
    Quiz
    0.07
    _xx
    0.07
    quiz
    0.07
     Quiz
    0.07
     excessive
    0.07
    izzes
    0.06
    _quiz
    0.06
     jue
    0.06
    Act Density 0.001%

    No Known Activations