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

    Neuronpedia

    INDEX
    Explanations

    improve performance and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    something
    0.19
     Современ
    0.18
     красивые
    0.17
     படங்கள்
    0.17
    辆
    0.17
     большие
    0.16
     capitán
    0.16
     شيء
    0.16
    سام
    0.16
     পর্যাপ্ত
    0.16
    POSITIVE LOGITS
     the
    0.38
     overall
    0.33
     how
    0.32
     its
    0.31
     their
    0.31
     deren
    0.28
    大家的
    0.27
     availability
    0.26
     accessibility
    0.25
     ಅದರ
    0.24
    Act Density 0.212%

    No Known Activations