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

    Neuronpedia

    INDEX
    Explanations

    C++ print statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ವಾ
    0.82
     chatId
    0.81
    ﷲ
    0.79
    eventType
    0.77
    λε
    0.77
     Writ
    0.77
     inputFile
    0.76
     ruido
    0.76
     DBHelper
    0.75
     Seeger
    0.75
    POSITIVE LOGITS
    问题
    0.71
     Converting
    0.67
    ক্ষম
    0.67
    din
    0.67
    내
    0.67
     Quer
    0.66
    Works
    0.66
    Quer
    0.66
    следование
    0.66
     As
    0.65
    Act Density 0.048%

    No Known Activations