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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ニニ
    -0.07
    템
    -0.07
    CompanyName
    -0.06
     rift
    -0.06
     ApplicationRecord
    -0.06
    Three
    -0.06
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.06
    Å
    -0.06
    .lib
    -0.06
    Ymd
    -0.06
    POSITIVE LOGITS
     IMD
    0.07
    tails
    0.07
    pletion
    0.07
    来说
    0.06
    媒体
    0.06
    _EDIT
    0.06
     prov
    0.06
    انیا
    0.06
    issue
    0.06
    اسي
    0.06
    Act Density 0.000%

    No Known Activations