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

    Neuronpedia

    INDEX
    Explanations

    applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่เป
    -0.07
    oder
    -0.07
     table
    -0.06
    ioc
    -0.06
    ongo
    -0.06
     дальней
    -0.06
     Eight
    -0.06
     deine
    -0.06
     numbers
    -0.06
    URRED
    -0.06
    POSITIVE LOGITS
     bli
    0.06
     چیست
    0.06
     fascination
    0.06
     رابط
    0.06
     редак
    0.06
     iş
    0.06
    Compose
    0.06
    //------------------------------------------------------------------------------↵
    0.06
     implications
    0.06
    .ll
    0.06
    Act Density 0.019%

    No Known Activations