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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Supply
    -0.08
    wią
    -0.07
    县委
    -0.07
    <Type
    -0.07
    不信
    -0.07
     invent
    -0.07
    ively
    -0.07
     births
    -0.06
    你們
    -0.06
    ão
    -0.06
    POSITIVE LOGITS
     нескольких
    0.07
    叁
    0.07
    악
    0.07
    Pot
    0.07
    世界各地
    0.07
     sme
    0.07
    趺
    0.07
    Segment
    0.07
    _CHO
    0.06
    鲭
    0.06
    Act Density 0.027%

    No Known Activations