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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    张先生
    -0.08
     товаров
    -0.07
    abbix
    -0.07
     Dataset
    -0.07
     Alejandro
    -0.07
    免责声明
    -0.07
     acheter
    -0.07
     الجديد
    -0.07
    Ⓞ
    -0.07
    那么简单
    -0.06
    POSITIVE LOGITS
    isc
    0.07
     foul
    0.07
    groupBy
    0.07
    莉
    0.07
    brane
    0.07
    jal
    0.07
    Big
    0.06
    (Code
    0.06
    opies
    0.06
    𝖐
    0.06
    Act Density 0.017%

    No Known Activations