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

    Neuronpedia

    INDEX
    Explanations

    words starting with di

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ې
    0.46
    جا
    0.41
    う
    0.40
    和平
    0.40
     جوئے
    0.39
    文字列
    0.39
    )});
    0.38
     Join
    0.38
    ט
    0.38
     join
    0.37
    POSITIVE LOGITS
     Di
    0.63
     diaries
    0.57
    Di
    0.57
     Диа
    0.56
     डाय
    0.54
     diat
    0.54
     DI
    0.53
     ディ
    0.53
     Ди
    0.52
     Diaries
    0.52
    Act Density 0.034%

    No Known Activations