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

    Neuronpedia

    INDEX
    Explanations

    capacity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    王
    -0.07
     winners
    -0.07
     see
    -0.07
     sees
    -0.07
    files
    -0.07
    _big
    -0.07
    东
    -0.07
    metry
    -0.07
     storia
    -0.07
     폴
    -0.07
    POSITIVE LOGITS
     capacity
    0.08
     Capacity
    0.08
    Capacity
    0.07
    طاق
    0.07
    .cent
    0.07
    .attack
    0.07
    ам
    0.07
    ья
    0.06
     вмест
    0.06
    ProgressHUD
    0.06
    Act Density 0.013%

    No Known Activations