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

    Neuronpedia

    INDEX
    Explanations

    Time-related words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adeon
    -0.07
    ements
    -0.07
    orders
    -0.07
    信访
    -0.07
     movements
    -0.07
    .ResponseBody
    -0.07
    表现为
    -0.07
    发烧
    -0.07
    จำหน
    -0.07
    ảnh
    -0.07
    POSITIVE LOGITS
    Credit
    0.07
     Indones
    0.07
     intuit
    0.07
     useParams
    0.07
     tert
    0.07
     היתר
    0.07
     titulo
    0.07
     postData
    0.07
     `,
    0.06
    LEV
    0.06
    Act Density 0.011%

    No Known Activations