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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     domestic
    -0.07
     bedeut
    -0.07
     bát
    -0.06
    vara
    -0.06
     NSUInteger
    -0.06
     сучас
    -0.06
     ice
    -0.06
    -strip
    -0.06
     CATEGORY
    -0.06
     حيث
    -0.06
    POSITIVE LOGITS
     Income
    0.07
     workload
    0.07
    fte
    0.06
    -role
    0.06
     глу
    0.06
    Founder
    0.06
     Dating
    0.06
    jsp
    0.06
     yelled
    0.06
    例
    0.06
    Act Density 0.055%

    No Known Activations