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

    Neuronpedia

    INDEX
    Explanations

    fugitives/arrest warrants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    انگلیسی
    -0.07
    Researchers
    -0.06
    /blog
    -0.06
    Ohio
    -0.06
     Maine
    -0.06
    Think
    -0.06
    interactive
    -0.06
     spanning
    -0.06
    ۳۶
    -0.06
    โรงแรม
    -0.06
    POSITIVE LOGITS
     MS
    0.07
     uns
    0.07
    ="?
    0.07
     rnd
    0.07
     назад
    0.06
    .sum
    0.06
    (today
    0.06
     @[
    0.06
    ponsor
    0.06
     "'
    0.06
    Act Density 0.038%

    No Known Activations