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

    Neuronpedia

    INDEX
    Explanations

    class/object names and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सुनेंरोक
    0.61
    калә
    0.61
     ईमित्र
    0.57
    🏧
    0.56
     NuGet
    0.55
     //-->
    0.55
    يميديا
    0.54
    薁
    0.54
    ChooseServer
    0.52
     вашу
    0.52
    POSITIVE LOGITS
    0.63
    p
    0.53
    Р
    0.52
      
    0.50
    ,
    0.50
    В
    0.50
    И
    0.50
    अ
    0.49
     “
    0.49
    О
    0.48
    Act Density 0.000%

    No Known Activations