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

    Neuronpedia

    INDEX
    Explanations

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _python
    -0.07
     Mary
    -0.07
    _third
    -0.07
     Wo
    -0.07
     Oliver
    -0.06
     Rosen
    -0.06
    CELER
    -0.06
     slash
    -0.06
     Furniture
    -0.06
     Manga
    -0.06
    POSITIVE LOGITS
     ün
    0.06
     Judicial
    0.06
    iar
    0.06
     cuid
    0.06
     hữu
    0.06
     탐
    0.06
     �
    0.06
    يق
    0.06
    yı
    0.06
     बह
    0.06
    Act Density 0.013%

    No Known Activations