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

    Neuronpedia

    INDEX
    Explanations

    granted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    těž
    -0.06
     było
    -0.06
     未
    -0.06
    жи
    -0.06
    wd
    -0.06
     blindly
    -0.06
    .GetBytes
    -0.06
    远
    -0.06
     другим
    -0.06
    tribution
    -0.06
    POSITIVE LOGITS
    bdd
    0.06
     країн
    0.06
     charities
    0.06
     woven
    0.06
     Tracking
    0.06
    uffer
    0.06
     rodin
    0.06
     ndarray
    0.06
     allerdings
    0.06
    331
    0.06
    Act Density 0.001%

    No Known Activations