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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vehicles
    -0.07
    不明白
    -0.07
     первой
    -0.07
     nevertheless
    -0.07
    .getType
    -0.07
    ILLISECONDS
    -0.07
    .Components
    -0.07
    踅
    -0.06
    erview
    -0.06
    _DOC
    -0.06
    POSITIVE LOGITS
    ADA
    0.08
    _bank
    0.07
    昆山
    0.06
     Алексан
    0.06
    足球
    0.06
    _Source
    0.06
    对外开放
    0.06
    isActive
    0.06
    Didn
    0.06
     Management
    0.06
    Act Density 0.004%

    No Known Activations