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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paras
    -0.07
     angl
    -0.06
     PIE
    -0.06
     które
    -0.06
     Bedrooms
    -0.06
    (reverse
    -0.06
     Niger
    -0.06
    ほ
    -0.06
    리를
    -0.06
     Plat
    -0.06
    POSITIVE LOGITS
    atel
    0.07
    �
    0.07
    /code
    0.06
    laps
    0.06
    alled
    0.06
    _documents
    0.06
    _cast
    0.06
    runs
    0.06
     PowerPoint
    0.06
     из
    0.06
    Act Density 0.069%

    No Known Activations