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

    Neuronpedia

    INDEX
    Explanations

    implement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MAT
    -0.08
     tầng
    -0.07
     ticker
    -0.06
    _bag
    -0.06
    Pages
    -0.06
    Constructor
    -0.06
    webpack
    -0.06
     Mek
    -0.06
     تلف
    -0.06
    슈
    -0.06
    POSITIVE LOGITS
    '}}>↵
    0.07
    rám
    0.06
    '),'
    0.06
    き
    0.06
    ременно
    0.06
    价
    0.06
    (js
    0.06
     seemed
    0.06
     ln
    0.06
     Σύ
    0.06
    Act Density 0.289%

    No Known Activations