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

    Neuronpedia

    INDEX
    Explanations

    word pairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cog
    -0.07
     Pix
    -0.07
     utilis
    -0.06
     ___
    -0.06
    초
    -0.06
    .Book
    -0.06
    大家
    -0.06
    áky
    -0.06
     wieder
    -0.06
    _im
    -0.06
    POSITIVE LOGITS
    Primitive
    0.07
     лицо
    0.07
    LETED
    0.07
    ف
    0.06
     proprietary
    0.06
    ynomials
    0.06
     transitional
    0.06
     보
    0.06
    ีฬา
    0.06
    opol
    0.06
    Act Density 0.035%

    No Known Activations