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

    Neuronpedia

    INDEX
    Explanations

    python `__name__`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鉆
    0.76
     পুর্ব
    0.66
     গেলো
    0.64
    𝗄
    0.63
    YR
    0.63
    тного
    0.61
     **/
    0.61
    াইয়
    0.60
    تالي
    0.60
     UICtrl
    0.60
    POSITIVE LOGITS
     herkes
    0.66
     berbicara
    0.62
     główn
    0.59
     صبح
    0.59
    CloseOperation
    0.58
     श्र
    0.58
     सुबह
    0.58
     книгу
    0.58
     Thursday
    0.57
     हिट
    0.55
    Act Density 0.947%

    No Known Activations