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

    Neuronpedia

    INDEX
    Explanations

    questions about cars

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    үр
    0.97
     incid
    0.92
     gebo
    0.92
     Receipts
    0.91
     glioma
    0.88
    чными
    0.87
     dvara
    0.86
     Physicians
    0.85
     системой
    0.84
    мин
    0.83
    POSITIVE LOGITS
    M
    0.77
    T
    0.77
    A
    0.75
    তার
    0.71
    flex
    0.68
    \[
    0.66
    ী
    0.66
    现状
    0.66
    간
    0.66
    Flex
    0.64
    Act Density 0.021%

    No Known Activations