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

    Neuronpedia

    INDEX
    Explanations

    Code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    质量
    -0.09
     quality
    -0.09
    EFR
    -0.08
     качество
    -0.08
     kalidad
    -0.08
     chọn
    -0.08
     directions
    -0.08
     ulag
    -0.08
    价格
    -0.08
     skyline
    -0.07
    POSITIVE LOGITS
     subclasses
    0.11
     superclass
    0.11
     Base
    0.11
    .Abstract
    0.11
     inherits
    0.10
    inherit
    0.10
    ancestor
    0.10
     inher
    0.10
    Base
    0.10
    Mixin
    0.10
    Act Density 0.013%

    No Known Activations