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

    Neuronpedia

    INDEX
    Explanations

    say "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Score
    -0.09
    .GetService
    -0.08
     scar
    -0.08
    查看全文
    -0.08
     Scar
    -0.07
     Sche
    -0.07
     생
    -0.07
    특별
    -0.07
     Tiên
    -0.07
    .BackgroundColor
    -0.07
    POSITIVE LOGITS
    控
    0.07
    (tuple
    0.06
    (log
    0.06
     process
    0.06
    错
    0.06
     commenting
    0.06
     hacen
    0.06
    כן
    0.06
    𫍽
    0.06
     GPUs
    0.06
    Act Density 0.014%

    No Known Activations