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

    Neuronpedia

    INDEX
    Explanations

    Stating a fact/argument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     that
    -0.08
     purs
    -0.07
    냥
    -0.06
    that
    -0.06
     journal
    -0.06
     envoy
    -0.06
    (that
    -0.06
     ник
    -0.06
     pharmac
    -0.06
    ردد
    -0.06
    POSITIVE LOGITS
     Stamford
    0.07
    闲
    0.07
     économ
    0.07
     رنگ
    0.06
    煙
    0.06
    ださい
    0.06
    Abstract
    0.06
    .Counter
    0.06
     영향
    0.06
    information
    0.06
    Act Density 0.188%

    No Known Activations