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

    Neuronpedia

    INDEX
    Explanations

    snapshot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thật
    -0.07
     Nina
    -0.07
    body
    -0.06
    ','','
    -0.06
    노출
    -0.06
     Bauer
    -0.06
     Đ
    -0.06
     variance
    -0.06
     cannons
    -0.06
    思考
    -0.06
    POSITIVE LOGITS
    II
    0.08
    (InputStream
    0.07
     esa
    0.07
     Перв
    0.07
    стор
    0.07
    ül
    0.06
    (second
    0.06
    ↵
↵
↵
    0.06
    decimal
    0.06
     Rapids
    0.06
    Act Density 0.000%

    No Known Activations