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

    Neuronpedia

    INDEX
    Explanations

    emancipation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ινε
    -0.07
    Beh
    -0.07
     Lear
    -0.07
     Geme
    -0.06
     lear
    -0.06
    남
    -0.06
    -eng
    -0.06
    iliation
    -0.06
    float
    -0.06
     знаю
    -0.06
    POSITIVE LOGITS
     Qualified
    0.07
    _column
    0.06
    .Inst
    0.06
     links
    0.06
    .updateDynamic
    0.06
    .Throws
    0.06
    <Response
    0.06
    说话
    0.06
     unrestricted
    0.06
     sofort
    0.06
    Act Density 0.006%

    No Known Activations