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

    Neuronpedia

    INDEX
    Explanations

    operator overloading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roupas
    0.42
     Shire
    0.39
     judicial
    0.39
     vestidos
    0.38
     nutrientes
    0.38
     cabinetry
    0.37
     옷
    0.37
     cutest
    0.37
     жид
    0.37
     WARRANT
    0.36
    POSITIVE LOGITS
    Operators
    0.52
    Operator
    0.48
    operator
    0.48
    operators
    0.47
     Operator
    0.46
     Operators
    0.44
    arc
    0.43
     operator
    0.43
     ar
    0.42
    arcs
    0.42
    Act Density 0.000%

    No Known Activations