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

    Neuronpedia

    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _on
    -0.07
    security
    -0.07
    Customers
    -0.07
     ee
    -0.06
    BACKGROUND
    -0.06
     stringent
    -0.06
    OUNTRY
    -0.06
    Addon
    -0.06
    _article
    -0.06
    -Based
    -0.06
    POSITIVE LOGITS
    真是
    0.07
     rav
    0.07
     зат
    0.07
    .paused
    0.06
     tehdy
    0.06
     Thankfully
    0.06
     thankfully
    0.06
     عمر
    0.06
     ale
    0.06
     εμπ
    0.06
    Act Density 0.047%

    No Known Activations