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

    Neuronpedia

    INDEX
    Explanations

    utf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    相见
    -0.07
    探访
    -0.07
    rice
    -0.07
     pioneering
    -0.07
     cooldown
    -0.06
    isman
    -0.06
    David
    -0.06
    Inject
    -0.06
    OPT
    -0.06
     retrieved
    -0.06
    POSITIVE LOGITS
     бюдж
    0.07
    orderby
    0.07
     Bols
    0.07
    ↱
    0.07
    饸
    0.07
     Ruf
    0.07
    价
    0.06
     Baby
    0.06
    ผลกระทบ
    0.06
    .str
    0.06
    Act Density 0.000%

    No Known Activations