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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LineColor
    -0.07
    ृ
    -0.06
     UserDao
    -0.06
     whitelist
    -0.06
    erg
    -0.06
    _soft
    -0.06
    postalcode
    -0.06
     Dob
    -0.06
     BaseController
    -0.06
     BaseType
    -0.05
    POSITIVE LOGITS
    相關
    0.07
     engages
    0.06
    ительные
    0.06
     득
    0.06
     kiểm
    0.06
     galleries
    0.06
    이며
    0.06
    .Group
    0.06
    >).
    0.06
    -columns
    0.06
    Act Density 0.018%

    No Known Activations