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

    Neuronpedia

    INDEX
    Explanations

    Common article and conjunction words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نوع
    -0.06
    _sd
    -0.06
    ]+'
    -0.06
    .album
    -0.06
    ابط
    -0.06
     upkeep
    -0.06
     Blaze
    -0.06
    .tag
    -0.06
    .rating
    -0.06
    .case
    -0.06
    POSITIVE LOGITS
     są
    0.06
    .toolbar
    0.06
    occus
    0.06
    {s
    0.06
    (jLabel
    0.06
    ны
    0.06
     nebo
    0.06
    楽し
    0.06
     talent
    0.06
    рут
    0.06
    Act Density 0.125%

    No Known Activations