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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مق
    -0.07
     )(
    -0.06
     reservations
    -0.06
    -friendly
    -0.06
     echoing
    -0.06
     interim
    -0.06
     παρ
    -0.06
    .dictionary
    -0.06
    Apps
    -0.06
    ale
    -0.06
    POSITIVE LOGITS
    .getX
    0.06
    ваем
    0.06
    eně
    0.06
    ώς
    0.06
     Jonas
    0.06
     spanish
    0.06
    .extra
    0.06
     startX
    0.06
    FormField
    0.05
     imágenes
    0.05
    Act Density 0.005%

    No Known Activations