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

    Neuronpedia

    INDEX
    Explanations

    introductions starting with this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     franche
    0.42
    থাৎ
    0.42
     그거
    0.41
     ایسا
    0.38
     blasts
    0.38
     ça
    0.37
     তাহা
    0.36
     takim
    0.36
     isso
    0.36
    роят
    0.36
    POSITIVE LOGITS
    この記事
    1.24
    本
    1.20
    本文
    1.18
    this
    1.15
     this
    1.12
    This
    1.05
     इस
    1.05
    この
    1.05
     questa
    1.05
    本書
    1.05
    Act Density 0.019%

    No Known Activations