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

    Neuronpedia

    INDEX
    Explanations

    describing states of nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ermöglichen
    0.28
     بتوان
    0.28
     sogenannten
    0.25
     ਆਪਣ
    0.25
     #${
    0.24
    噉
    0.24
    ።
    0.23
     ಯು
    0.23
    㺫
    0.23
    ۔
    0.23
    POSITIVE LOGITS
     isn
    0.39
     wasn
    0.38
     is
    0.37
     είναι
    0.37
     was
    0.36
     itself
    0.36
     seems
    0.35
     está
    0.35
     tiene
    0.34
     had
    0.33
    Act Density 0.201%

    No Known Activations