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

    Neuronpedia

    INDEX
    Explanations

    creative content and abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     etc
    0.57
    など
    0.55
    などで
    0.51
     тощо
    0.49
    などを
    0.47
     등이
    0.46
     등을
    0.44
     など
    0.44
    等
    0.43
     usw
    0.43
    POSITIVE LOGITS
    atorio
    0.42
    Roboto
    0.41
    ayutt
    0.39
    ższ
    0.38
    ირო
    0.37
    idot
    0.37
    щото
    0.37
    ertation
    0.37
    ーーーー
    0.37
     ಅದೇ
    0.37
    Act Density 0.147%

    No Known Activations