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

    Neuronpedia

    INDEX
    Explanations

    eclipse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .room
    -0.07
    RF
    -0.07
    =./
    -0.06
     fetched
    -0.06
     Motor
    -0.06
    DataProvider
    -0.06
     prod
    -0.06
    ORD
    -0.06
    .Operator
    -0.06
     بر
    -0.06
    POSITIVE LOGITS
     Eclipse
    0.09
    clipse
    0.08
    .eclipse
    0.08
    -NLS
    0.07
     propane
    0.07
     eclipse
    0.06
     Dahl
    0.06
    getClass
    0.06
     luggage
    0.06
     Wesley
    0.06
    Act Density 0.002%

    No Known Activations