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

    Neuronpedia

    INDEX
    Explanations

    Academic journals/publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Truy
    -0.07
    UIKit
    -0.06
    ."""↵
    -0.06
     CircularProgressIndicator
    -0.06
     INSTALL
    -0.06
     Schn
    -0.06
    .smart
    -0.06
     kk
    -0.06
    でしょう
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    POSITIVE LOGITS
     logging
    0.06
     보고
    0.06
    ьи
    0.06
     tiết
    0.06
     oddly
    0.06
     anomalies
    0.06
    增加
    0.06
    pizza
    0.06
     réponse
    0.06
    飞
    0.06
    Act Density 0.032%

    No Known Activations