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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ￭
    -0.07
    Ext
    -0.07
    降
    -0.07
    част
    -0.07
    карт
    -0.07
     Bridge
    -0.07
    iculos
    -0.07
    Flight
    -0.07
    蟏
    -0.06
    长大了
    -0.06
    POSITIVE LOGITS
    /output
    0.08
     شيء
    0.07
    (ok
    0.07
    .theme
    0.07
     yards
    0.06
     analyzing
    0.06
     Bryant
    0.06
    ليل
    0.06
    ,param
    0.06
     reco
    0.06
    Act Density 0.002%

    No Known Activations