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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    р
    -0.07
     luckily
    -0.07
    /article
    -0.06
     hr
    -0.06
    岗
    -0.06
     Bracket
    -0.06
    pagination
    -0.06
    aur
    -0.06
    商品房
    -0.06
     do
    -0.06
    POSITIVE LOGITS
    (`${
    0.08
    Playlist
    0.07
     yaş
    0.07
    قضي
    0.07
    ONLY
    0.06
    $text
    0.06
     Favorite
    0.06
    �
    0.06
    祛
    0.06
     fleeting
    0.06
    Act Density 0.011%

    No Known Activations