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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     circumstance
    -0.09
     Katr
    -0.08
     Mein
    -0.07
     Wisdom
    -0.07
     수도
    -0.07
     circunst
    -0.07
     $("#"
    -0.07
    天津
    -0.07
     circonstances
    -0.07
     circumstances
    -0.07
    POSITIVE LOGITS
    href
    0.09
     responsiveness
    0.09
     href
    0.09
     willow
    0.09
     crawl
    0.09
     HTTPS
    0.09
     hre
    0.09
     gluten
    0.09
     favicon
    0.08
    /favicon
    0.08
    Act Density 0.016%

    No Known Activations