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

    Neuronpedia

    INDEX
    Explanations

    fit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    copies
    -0.07
    Scheduler
    -0.07
    umbo
    -0.06
     Consumption
    -0.06
    Save
    -0.06
     colored
    -0.06
    HomePage
    -0.06
    行动
    -0.06
    active
    -0.06
     glacier
    -0.06
    POSITIVE LOGITS
     Gundam
    0.06
    (an
    0.06
    Natural
    0.06
     Natural
    0.06
    không
    0.06
     within
    0.06
    :Set
    0.06
     Whatever
    0.06
     rotterdam
    0.06
    _conn
    0.06
    Act Density 0.003%

    No Known Activations