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

    Neuronpedia

    INDEX
    Explanations

    parentheses and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %
    -0.07
     Given
    -0.06
    }:
    -0.06
    (model
    -0.06
     Neh
    -0.06
     Schwartz
    -0.06
     democracy
    -0.06
     property
    -0.06
    ource
    -0.06
     recruitment
    -0.06
    POSITIVE LOGITS
    .rstrip
    0.08
    ращи
    0.07
    toFixed
    0.07
     Dynamo
    0.07
     إلى
    0.07
     filetype
    0.07
     замов
    0.07
    寶
    0.07
    ύπ
    0.06
     Battalion
    0.06
    Act Density 0.039%

    No Known Activations