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

    Neuronpedia

    INDEX
    Explanations

    say "hours"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     function
    -0.07
     documentary
    -0.07
    ;|
    -0.06
    function
    -0.06
    НА
    -0.06
     uniformly
    -0.06
    BO
    -0.06
     함수
    -0.06
    adj
    -0.06
    Chapter
    -0.06
    POSITIVE LOGITS
     변
    0.07
     東京
    0.06
     رنگ
    0.06
     Bran
    0.06
     Kepler
    0.06
     Alonso
    0.06
     Tulsa
    0.06
    ΕΣ
    0.06
    peak
    0.06
     Brennan
    0.06
    Act Density 0.008%

    No Known Activations