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

    Neuronpedia

    INDEX
    Explanations

    brackets/parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     변수
    -0.07
     Veteran
    -0.07
     Betty
    -0.07
    _LENGTH
    -0.07
    ONLY
    -0.07
     tổ
    -0.07
    aussian
    -0.07
    TabPage
    -0.06
    .`,↵
    -0.06
    Group
    -0.06
    POSITIVE LOGITS
    десь
    0.07
     calculated
    0.07
     MCS
    0.07
     DOT
    0.06
    (pages
    0.06
    筜
    0.06
    ときは
    0.06
    /moment
    0.06
    עמיד
    0.06
     wield
    0.06
    Act Density 0.038%

    No Known Activations