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

    Neuronpedia

    INDEX
    Explanations

    poem snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <DateTime
    -0.08
    pong
    -0.07
     Often
    -0.07
    تعا
    -0.07
    不做
    -0.06
    冻
    -0.06
    画家
    -0.06
    党的建设
    -0.06
     conson
    -0.06
     муж
    -0.06
    POSITIVE LOGITS
    '];?>
    0.07
     Kurds
    0.07
    >//
    0.06
    .receive
    0.06
    מקור
    0.06
    hind
    0.06
    *>&
    0.06
     ,(
    0.06
    nız
    0.06
     özellikleri
    0.06
    Act Density 0.001%

    No Known Activations