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

    Neuronpedia

    INDEX
    Explanations

    bolded text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    traj
    -0.08
    아요
    -0.08
     عليك
    -0.08
    Ordered
    -0.08
    ға
    -0.08
    Ά
    -0.08
     ಇಲ್ಲ
    -0.08
    어요
    -0.08
    IIII
    -0.08
     এখানে
    -0.08
    POSITIVE LOGITS
     Lastly
    0.09
     završ
    0.08
     crowds
    0.08
     führen
    0.07
     Enfin
    0.07
     letzt
    0.07
    Lastly
    0.07
     mentoring
    0.07
     Selenium
    0.07
     documentation
    0.07
    Act Density 0.082%

    No Known Activations