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

    Neuronpedia

    INDEX
    Explanations

    Code/register definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    timeline
    -0.07
     Hopkins
    -0.07
    期间
    -0.07
     بوده
    -0.07
     دن
    -0.07
     suggesting
    -0.07
     IDR
    -0.07
     Andre
    -0.07
     Tout
    -0.07
    نش
    -0.06
    POSITIVE LOGITS
    _lcd
    0.06
    .util
    0.06
    plat
    0.06
     mystical
    0.06
    actory
    0.06
     sque
    0.05
    中文
    0.05
     आर
    0.05
     фон
    0.05
    フェ
    0.05
    Act Density 0.013%

    No Known Activations