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

    Neuronpedia

    INDEX
    Explanations

    personal favorites and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ƌ
    0.76
     단위
    0.72
     jednost
    0.71
     шту
    0.69
    笼
    0.69
     ইউনিট
    0.66
     evident
    0.66
    upta
    0.65
    WindowEvent
    0.64
     వ్యవస్థ
    0.64
    POSITIVE LOGITS
     favorite
    3.38
     favourite
    3.05
    favorite
    2.92
    Favorite
    2.78
     favorites
    2.77
     Favorite
    2.76
    Favourite
    2.62
     Favourite
    2.56
     Lieblings
    2.47
     favourites
    2.36
    Act Density 0.182%

    No Known Activations