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

    Neuronpedia

    INDEX
    Explanations

    station

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Time
    -0.07
    bold
    -0.07
     tooltip
    -0.07
     Introduction
    -0.07
    ra
    -0.06
     welt
    -0.06
    iting
    -0.06
    弄
    -0.06
    eyn
    -0.06
    portunity
    -0.06
    POSITIVE LOGITS
     stations
    0.08
     station
    0.06
     ваг
    0.06
    �ng
    0.06
    σχ
    0.06
     Station
    0.06
     Stations
    0.06
    คร
    0.06
    lington
    0.06
     gyro
    0.06
    Act Density 0.002%

    No Known Activations