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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fingertips
    -0.07
    侣
    -0.07
     graceful
    -0.06
    头顶
    -0.06
    پ
    -0.06
    pped
    -0.06
    .sms
    -0.06
    Instead
    -0.06
    少许
    -0.06
    来自于
    -0.06
    POSITIVE LOGITS
    .Columns
    0.09
    енная
    0.08
    行為
    0.07
     Điều
    0.07
    婍
    0.06
     Sorted
    0.06
     drives
    0.06
    造林
    0.06
     Mission
    0.06
     Drinking
    0.06
    Act Density 0.003%

    No Known Activations