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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     설
    -0.08
    Array
    -0.07
     visits
    -0.07
    /filter
    -0.07
    -slide
    -0.06
     Cabr
    -0.06
     YYYY
    -0.06
     Slider
    -0.06
     Hawks
    -0.06
     측
    -0.06
    POSITIVE LOGITS
    (aa
    0.06
    배송
    0.06
    queen
    0.06
    ování
    0.06
    )i
    0.06
     bedrooms
    0.06
    /h
    0.06
    preh
    0.06
    -task
    0.06
     pic
    0.06
    Act Density 0.010%

    No Known Activations