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

    Neuronpedia

    INDEX
    Explanations

    event announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Certain
    -0.06
     ninth
    -0.06
     hitter
    -0.06
    iteration
    -0.06
    нему
    -0.06
     ثابت
    -0.06
     ||=
    -0.06
    ΗΜ
    -0.06
     hemos
    -0.06
    Во
    -0.06
    POSITIVE LOGITS
    272
    0.07
    281
    0.06
    (MainActivity
    0.06
    peaker
    0.06
     UCS
    0.06
     downloads
    0.06
    نویس
    0.06
    (scan
    0.06
    [field
    0.06
    ...");↵↵
    0.06
    Act Density 0.083%

    No Known Activations