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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    он
    -0.08
     occ
    -0.07
     куда
    -0.07
     му
    -0.06
     obtain
    -0.06
     arranged
    -0.06
     фа
    -0.06
     renal
    -0.06
     Vulkan
    -0.06
     ADDR
    -0.06
    POSITIVE LOGITS
    死者
    0.07
    _:*
    0.07
    是一种
    0.07
    릭
    0.07
     engines
    0.06
    ratio
    0.06
    耜
    0.06
     generally
    0.06
    ރ
    0.06
    `)↵
    0.06
    Act Density 0.000%

    No Known Activations