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

    Neuronpedia

    INDEX
    Explanations

    reading and viewing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CreateTable
    1.04
     innovate
    1.00
     innovation
    0.98
     innovating
    0.97
     разрабаты
    0.96
     innovación
    0.95
    ICreate
    0.93
     innovator
    0.92
     উদ্ভাব
    0.92
     creat
    0.90
    POSITIVE LOGITS
     reading
    1.85
     Reading
    1.75
    reading
    1.67
    Reading
    1.67
    阅读
    1.55
     READING
    1.51
     membaca
    1.41
     viewing
    1.40
    閱讀
    1.39
     lectura
    1.39
    Act Density 0.566%

    No Known Activations