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

    Neuronpedia

    INDEX
    Explanations

    Citations or bibliography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mag
    -0.07
    anes
    -0.07
    ْت
    -0.07
    цем
    -0.06
     배열
    -0.06
     trophy
    -0.06
     Falls
    -0.06
     sweaty
    -0.06
     interactive
    -0.06
     lively
    -0.06
    POSITIVE LOGITS
    .amount
    0.07
     ds
    0.06
    @Json
    0.06
     DateFormat
    0.06
     odom
    0.06
     mileage
    0.06
     ///</
    0.06
     Heading
    0.06
    traffic
    0.06
    >{
    0.06
    Act Density 0.016%

    No Known Activations