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

    Neuronpedia

    INDEX
    Explanations

    Research papers/citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    กำหนด
    -0.07
     зелен
    -0.06
    European
    -0.06
     Winn
    -0.06
    肯
    -0.06
     visualization
    -0.06
     Европ
    -0.06
    POCH
    -0.06
     chức
    -0.06
    内容
    -0.06
    POSITIVE LOGITS
     DateFormat
    0.07
    (exports
    0.07
    ">',
    0.07
     Aralık
    0.06
     Odds
    0.06
    .stdin
    0.06
    (substr
    0.06
    /pi
    0.06
     Şubat
    0.06
    อบ
    0.06
    Act Density 0.030%

    No Known Activations