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

    Neuronpedia

    INDEX
    Explanations

    message

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    пион
    -0.07
    /Subthreshold
    -0.06
    .’”↵↵
    -0.06
    (always
    -0.06
    TRIES
    -0.06
     rookies
    -0.06
    (identifier
    -0.06
     먼
    -0.06
    [list
    -0.06
    upp
    -0.06
    POSITIVE LOGITS
     khuyến
    0.07
    iola
    0.06
     Hod
    0.06
     softball
    0.06
     Odd
    0.06
    Hey
    0.06
    idue
    0.06
    \Notifications
    0.06
     whispered
    0.06
    xCD
    0.06
    Act Density 0.027%

    No Known Activations