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

    Neuronpedia

    INDEX
    Explanations

    concluding or summarizing phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    两天
    0.85
    Optional
    0.83
    łych
    0.78
    有一些
    0.77
    Further
    0.77
    lng
    0.76
     اليوم
    0.76
    vcn
    0.75
    further
    0.75
    serializing
    0.75
    POSITIVE LOGITS
     conclusion
    1.78
    Conclusion
    1.69
     Conclusion
    1.64
     Conclusions
    1.44
     CONCLUSION
    1.43
    Conclusions
    1.39
    conclusion
    1.37
     conclusions
    1.35
    结论
    1.31
    CONCLUSION
    1.30
    Act Density 0.067%

    No Known Activations