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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    澹
    -0.07
    Mark
    -0.07
    蒨
    -0.07
     Sunshine
    -0.07
    ublisher
    -0.07
    (run
    -0.07
    �
    -0.06
    �
    -0.06
    pute
    -0.06
     Cant
    -0.06
    POSITIVE LOGITS
     делать
    0.07
    Hit
    0.07
     OTHER
    0.07
    פג
    0.07
    ẠI
    0.07
    Presentation
    0.07
    �
    0.07
     "\">
    0.07
    וף
    0.07
    流域
    0.07
    Act Density 0.001%

    No Known Activations