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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ан
    -0.07
    package
    -0.06
     legislature
    -0.06
    CLA
    -0.06
     STL
    -0.06
    ени
    -0.06
     Aud
    -0.06
     protobuf
    -0.06
     campuses
    -0.06
     lai
    -0.06
    POSITIVE LOGITS
    usual
    0.09
    _FINAL
    0.07
    剂
    0.07
    》（
    0.07
    онах
    0.06
     khối
    0.06
    ＼＼
    0.06
     اختصاص
    0.06
    čního
    0.06
     startIndex
    0.06
    Act Density 0.066%

    No Known Activations