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

    Neuronpedia

    INDEX
    Explanations

    mixed data with numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bans
    -0.07
    .Schedule
    -0.07
    .keras
    -0.06
    _EXPECT
    -0.06
    σμού
    -0.06
     hlavy
    -0.06
    nosti
    -0.06
     tam
    -0.06
     /[
    -0.06
    .settings
    -0.06
    POSITIVE LOGITS
    디
    0.07
    Scotland
    0.06
     Prague
    0.06
     NASA
    0.06
     --↵↵
    0.06
    ilies
    0.06
    컨
    0.06
     BUSINESS
    0.06
     Tools
    0.06
    ulse
    0.06
    Act Density 0.000%

    No Known Activations