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

    Neuronpedia

    INDEX
    Explanations

    Schedules or itineraries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kindle
    -0.07
    ondere
    -0.07
    .Now
    -0.07
    תקווה
    -0.07
    רצה
    -0.06
    Sports
    -0.06
    gray
    -0.06
    isman
    -0.06
    ศาล
    -0.06
    .gif
    -0.06
    POSITIVE LOGITS
    %"
    0.07
    啸
    0.07
    _funcs
    0.07
    Ά
    0.07
    (hist
    0.07
    ENCHMARK
    0.06
     Dimensions
    0.06
    _condition
    0.06
    斌
    0.06
    申し込み
    0.06
    Act Density 0.022%

    No Known Activations