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

    Neuronpedia

    INDEX
    Explanations

    BI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pow
    -0.07
    imulation
    -0.07
    kır
    -0.07
    ilenames
    -0.07
    ><![
    -0.06
    重点
    -0.06
    čil
    -0.06
    curities
    -0.06
     ".");↵
    -0.06
    ılıp
    -0.06
    POSITIVE LOGITS
     Le
    0.07
    иль
    0.07
    Banner
    0.07
     Naj
    0.06
     banner
    0.06
    斷
    0.06
    思い
    0.06
     Auto
    0.06
     assembling
    0.06
     promotional
    0.06
    Act Density 0.002%

    No Known Activations