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

    Neuronpedia

    INDEX
    Explanations

    lying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ScrollPane
    -0.07
    тро
    -0.07
     Angela
    -0.07
     Infant
    -0.07
     podcasts
    -0.06
    олог
    -0.06
    pay
    -0.06
    ﭸ
    -0.06
     getApp
    -0.06
     appliance
    -0.06
    POSITIVE LOGITS
    Rename
    0.08
    Q
    0.07
    duplicate
    0.07
    一個
    0.07
    ("\"
    0.07
    every
    0.07
     metres
    0.07
     Kısa
    0.07
     (*(
    0.07
    icates
    0.07
    Act Density 0.174%

    No Known Activations