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

    Neuronpedia

    INDEX
    Explanations

    scientific analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AM
    -0.07
    departureday
    -0.07
     그러나
    -0.06
     دین
    -0.06
     instead
    -0.06
     tecr
    -0.06
    distribution
    -0.06
    <count
    -0.06
    ़ी
    -0.06
    以为
    -0.06
    POSITIVE LOGITS
    كي
    0.07
    Leap
    0.07
    429
    0.07
    .registry
    0.07
     newPos
    0.07
     BufferedImage
    0.06
    iras
    0.06
    iffe
    0.06
     CBS
    0.06
     Suns
    0.06
    Act Density 0.000%

    No Known Activations