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

    Neuronpedia

    INDEX
    Explanations

    concepts and vibes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ;
    0.32
    their
    0.31
    로부터
    0.31
    并通过
    0.28
     sejumlah
    0.28
    ၏
    0.28
     successfully
    0.28
    具有
    0.28
    sthe
    0.27
    each
    0.27
    POSITIVE LOGITS
    感慨
    0.47
     기다
    0.44
     сожа
    0.44
     걱
    0.44
     preocupaciones
    0.43
     질문
    0.43
     воспомина
    0.41
     উদ্বেগ
    0.41
     revelations
    0.40
     regrets
    0.39
    Act Density 0.094%

    No Known Activations