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

    Neuronpedia

    INDEX
    Explanations

    Impact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -initial
    -0.07
    _item
    -0.07
     unpopular
    -0.07
     Pascal
    -0.07
     Cannes
    -0.06
    *)(
    -0.06
    나라
    -0.06
    ايل
    -0.06
    /Grid
    -0.06
     Aure
    -0.06
    POSITIVE LOGITS
     spir
    0.07
     ≤
    0.06
     XCTestCase
    0.06
    rial
    0.06
     broaden
    0.06
     ap
    0.06
     lowered
    0.06
     Buyer
    0.06
     encour
    0.06
     pró
    0.06
    Act Density 0.156%

    No Known Activations