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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cate
    -0.06
    َب
    -0.06
    ressed
    -0.06
     centuries
    -0.06
     recalled
    -0.06
    ardır
    -0.06
    November
    -0.06
     thường
    -0.06
    795
    -0.06
    _amt
    -0.06
    POSITIVE LOGITS
    сяг
    0.07
     lug
    0.07
     Muham
    0.06
    .FIELD
    0.06
    --;
    0.06
    拥有
    0.06
    οι
    0.06
    ώς
    0.06
     zvlá
    0.06
     лю
    0.06
    Act Density 0.010%

    No Known Activations