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

    Neuronpedia

    INDEX
    Explanations

    focused on applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सफाई
    0.45
     ი
    0.45
     노
    0.44
    的总
    0.44
    的变化
    0.44
     gră
    0.44
     های
    0.44
     ď
    0.44
     وہ
    0.43
     එය
    0.43
    POSITIVE LOGITS
    Xiaomi
    0.46
     Задача
    0.45
    Muchas
    0.43
    %%\
    0.43
    का
    0.43
    encountered
    0.43
    Dok
    0.43
    Те
    0.43
    bim
    0.43
    Nothing
    0.42
    Act Density 0.000%

    No Known Activations