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

    Neuronpedia

    INDEX
    Explanations

    classifier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    测定
    -0.08
    原创
    -0.08
    中秋
    -0.08
     Guid
    -0.07
     irresponsible
    -0.07
     Rounded
    -0.07
     một
    -0.07
     Creat
    -0.07
     yuk
    -0.07
     ebony
    -0.07
    POSITIVE LOGITS
     regimen
    0.07
    Ｊ
    0.07
    ನ
    0.07
    uffix
    0.07
    -Semitism
    0.06
     verschied
    0.06
    -Cola
    0.06
     cred
    0.06
     orbits
    0.06
     ↵	↵
    0.06
    Act Density 0.002%

    No Known Activations