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

    Neuronpedia

    INDEX
    Explanations

    code and technical jargon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    party
    -0.06
     había
    -0.06
     davon
    -0.06
     embraces
    -0.06
    wal
    -0.06
     yet
    -0.06
     uncompressed
    -0.06
     говорит
    -0.06
     submits
    -0.06
    456
    -0.06
    POSITIVE LOGITS
    .points
    0.07
    career
    0.07
    requ
    0.07
     제작
    0.06
     guar
    0.06
     замі
    0.06
    icators
    0.06
     Eylül
    0.06
    alysis
    0.06
    존
    0.06
    Act Density 0.000%

    No Known Activations