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

    Neuronpedia

    INDEX
    Explanations

    concluding sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ощущения
    0.28
    芎
    0.27
     extraordinarily
    0.25
     ObjData
    0.25
    artista
    0.25
    рифмети
    0.25
    Locale
    0.25
    Ordenar
    0.24
    ವರಿ
    0.24
     casings
    0.24
    POSITIVE LOGITS
     concludes
    0.37
     Conclusion
    0.35
     conclusion
    0.34
     결
    0.33
    Conclusion
    0.33
    निष्कर्ष
    0.32
    conclusion
    0.31
     concluded
    0.31
     CONCLUSION
    0.31
     concluding
    0.30
    Act Density 0.034%

    No Known Activations