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

    Neuronpedia

    INDEX
    Explanations

    software/books

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    coupon
    -0.07
    gal
    -0.06
    vail
    -0.06
    affles
    -0.06
     Ads
    -0.06
    мени
    -0.06
    ียงใหม
    -0.06
     каждый
    -0.06
     Trailer
    -0.06
     eag
    -0.06
    POSITIVE LOGITS
    (async
    0.06
     departing
    0.06
     conferences
    0.06
    $",
    0.06
    .notify
    0.06
    -topic
    0.06
    .`);↵
    0.06
     paragraphs
    0.06
    ﾄ
    0.06
    $',
    0.06
    Act Density 0.000%

    No Known Activations