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

    Neuronpedia

    INDEX
    Explanations

    parties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Twitter
    -0.06
    794
    -0.06
    úng
    -0.06
    aría
    -0.06
    .push
    -0.06
    ublisher
    -0.06
     warmer
    -0.06
     california
    -0.06
     calf
    -0.06
    usta
    -0.06
    POSITIVE LOGITS
    )a
    0.07
     avenues
    0.07
    rolley
    0.06
    基本
    0.06
    )),
    0.06
     yıllık
    0.06
    roti
    0.06
     Reset
    0.06
     Кар
    0.06
     pac
    0.06
    Act Density 0.003%

    No Known Activations