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

    Neuronpedia

    INDEX
    Explanations

    uncertainty indicators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .col
    -0.07
    еления
    -0.07
    рист
    -0.07
    (Adapter
    -0.06
     श
    -0.06
     IDisposable
    -0.06
    ští
    -0.06
     المع
    -0.06
    hos
    -0.06
     tren
    -0.06
    POSITIVE LOGITS
    Ù
    0.07
     stability
    0.07
     Returns
    0.07
     infertility
    0.06
    VC
    0.06
     bomb
    0.06
    Post
    0.06
    conexion
    0.06
    ーバ
    0.06
     fog
    0.06
    Act Density 0.010%

    No Known Activations