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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sector
    -0.06
    选择
    -0.06
    ровать
    -0.06
    (cin
    -0.06
     حرکت
    -0.06
     uluslararası
    -0.06
    ocrisy
    -0.06
     polluted
    -0.06
     bucket
    -0.06
     bishop
    -0.06
    POSITIVE LOGITS
     laisse
    0.07
    .Z
    0.06
     fName
    0.06
    Drupal
    0.06
    )x
    0.06
     axs
    0.06
     Benton
    0.06
    portfolio
    0.06
     rever
    0.06
     ξ
    0.06
    Act Density 0.011%

    No Known Activations