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

    Neuronpedia

    INDEX
    Explanations

    learning and tutorials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aad
    -0.10
     excluding
    -0.09
     Proxy
    -0.08
     excluir
    -0.08
     redact
    -0.08
    Qry
    -0.08
     colorectal
    -0.08
    -0.08
     qry
    -0.08
    Routing
    -0.08
    POSITIVE LOGITS
     beginner
    0.17
     beginners
    0.16
     Anfänger
    0.15
    教程
    0.14
     Beginner
    0.13
    初心
    0.13
     Beginners
    0.12
     apprenticeship
    0.12
     amateurs
    0.12
     amateur
    0.12
    Act Density 0.075%
    No Known Activations