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

    Neuronpedia

    INDEX
    Explanations

    ============

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stats
    -0.07
    .Ui
    -0.07
    的家庭
    -0.07
    老師
    -0.07
    ็บ
    -0.07
    Dat
    -0.07
     word
    -0.06
    .Book
    -0.06
     knocked
    -0.06
    Doc
    -0.06
    POSITIVE LOGITS
    整车
    0.07
    婧
    0.07
    :utf
    0.07
    珝
    0.07
     BorderLayout
    0.06
    .ButterKnife
    0.06
     GOLD
    0.06
     superClass
    0.06
    *v
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations