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

    Neuronpedia

    INDEX
    Explanations

    necessary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    地区的
    -0.08
    .process
    -0.07
    �
    -0.07
     RESP
    -0.07
     invest
    -0.07
     Hard
    -0.07
    �
    -0.07
    スピ
    -0.07
    egend
    -0.07
     Hubb
    -0.07
    POSITIVE LOGITS
    centage
    0.07
     saber
    0.07
    cription
    0.07
    фр
    0.07
    .InnerText
    0.06
    быт
    0.06
    icit
    0.06
    educated
    0.06
    fig
    0.06
    Percentage
    0.06
    Act Density 0.021%

    No Known Activations