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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     increasingly
    -0.07
     teor
    -0.07
    İR
    -0.06
     巴
    -0.06
     Emmanuel
    -0.06
    .Timestamp
    -0.06
     retailers
    -0.06
     perhaps
    -0.06
     luận
    -0.06
     použití
    -0.06
    POSITIVE LOGITS
    ्यव
    0.07
    няют
    0.06
     ********
    0.06
    _ETH
    0.06
    πή
    0.06
    _pdata
    0.06
    ustrial
    0.06
    _CELL
    0.06
     业
    0.06
     öncelik
    0.06
    Act Density 0.045%

    No Known Activations