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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feminist
    -0.07
    ">(
    -0.07
    есь
    -0.07
    uyên
    -0.07
    Helper
    -0.07
    ność
    -0.06
    \Log
    -0.06
     deeds
    -0.06
    dims
    -0.06
     된
    -0.06
    POSITIVE LOGITS
    Offer
    0.06
     FROM
    0.06
    anyl
    0.06
     Brass
    0.06
     Transform
    0.06
     from
    0.06
    έλ
    0.06
     Airlines
    0.06
    ErrorException
    0.05
    dish
    0.05
    Act Density 0.003%

    No Known Activations