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

    Neuronpedia

    INDEX
    Explanations

    code or math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不仅可以
    -0.09
    如果没有
    -0.07
     numberWith
    -0.06
     predicting
    -0.06
     charger
    -0.06
    戒
    -0.06
    [opt
    -0.06
    介绍说
    -0.06
    ʘ
    -0.06
    新闻记者
    -0.06
    POSITIVE LOGITS
     Cata
    0.07
     produção
    0.07
    :bold
    0.07
     '"'
    0.07
    殖
    0.07
    /Data
    0.07
    -mar
    0.07
    _DIFF
    0.07
    _ap
    0.07
     الدر
    0.07
    Act Density 0.006%

    No Known Activations