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

    Neuronpedia

    INDEX
    Explanations

    believed to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Evaluating
    0.41
     Allocation
    0.41
     অথচ
    0.40
    álním
    0.40
     WOMEN
    0.39
     получаем
    0.38
    㚐
    0.38
     Processes
    0.37
     посмотрим
    0.37
     Molecular
    0.37
    POSITIVE LOGITS
     essere
    0.68
     être
    0.63
     oleh
    0.61
     توسط
    0.58
     by
    0.57
    ว่าเป็น
    0.56
     द्वारा
    0.56
     многи
    0.54
     bý
    0.52
     být
    0.52
    Act Density 0.018%

    No Known Activations