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

    Neuronpedia

    INDEX
    Explanations

    animal actions and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appunto
    0.51
     Seriously
    0.44
    Seriously
    0.44
    なのです
    0.43
    Donc
    0.42
     portanto
    0.42
     म्हणूनच
    0.41
     właśnie
    0.41
     именно
    0.40
    그래서
    0.40
    POSITIVE LOGITS
     hingegen
    0.98
     ebenfalls
    0.92
     natomiast
    0.91
     similarly
    0.86
     likewise
    0.85
    同樣
    0.80
    同样
    0.76
     dagegen
    0.74
     kolei
    0.73
    こちらも
    0.73
    Act Density 0.022%

    No Known Activations