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

    Neuronpedia

    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,.
    -0.07
     birthdays
    -0.06
    (),↵↵
    -0.06
     operators
    -0.06
    로나
    -0.06
    _POOL
    -0.06
     wes
    -0.06
     Cette
    -0.06
     nhỏ
    -0.06
    orianCalendar
    -0.06
    POSITIVE LOGITS
    uling
    0.07
    AutoresizingMask
    0.07
    버
    0.06
    getCurrent
    0.06
     ответствен
    0.06
    اجات
    0.06
     PCIe
    0.06
     Tamil
    0.06
     السكان
    0.06
     출연
    0.06
    Act Density 0.006%

    No Known Activations