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

    Neuronpedia

    INDEX
    Explanations

    (list

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    邓小
    -0.08
    BigInteger
    -0.07
    籀
    -0.07
    🏺
    -0.07
     Metallic
    -0.07
    weit
    -0.07
    -0.07
    xcc
    -0.07
    抗癌
    -0.07
    ictionaries
    -0.07
    POSITIVE LOGITS
     stabil
    0.07
    有多
    0.07
    的好
    0.06
     Scratch
    0.06
     tol
    0.06
    ILLS
    0.06
    ầm
    0.06
     sights
    0.06
     Tender
    0.06
     Customize
    0.06
    Act Density 0.001%

    No Known Activations