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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Title
    -0.08
     Acres
    -0.08
     сотруд
    -0.06
    ，每
    -0.06
     bottoms
    -0.06
    องท
    -0.06
     توضی
    -0.06
     arrogant
    -0.06
     wastewater
    -0.06
    上了
    -0.06
    POSITIVE LOGITS
    UGIN
    0.07
    Mixin
    0.06
    ively
    0.06
    струмент
    0.06
    -im
    0.06
    empl
    0.06
    NewUrlParser
    0.06
     intermediary
    0.06
     biri
    0.06
     TRADE
    0.06
    Act Density 1.049%

    No Known Activations