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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ioneers
    -0.50
    accumulate
    -0.48
     savages
    -0.41
     economist
    -0.41
     aerodynamic
    -0.41
     socialists
    -0.41
     conqueror
    -0.41
     sinner
    -0.40
     cyc
    -0.40
     Merlot
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.92
    ArgsConstructor
    0.89
    CloseOperation
    0.88
     any
    0.86
    BeginContext
    0.82
    other
    0.80
     other
    0.80
     demais
    0.77
    XmlAccessorType
    0.75
    any
    0.73
    Act Density 0.001%

    No Known Activations