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

    Neuronpedia

    INDEX
    Explanations

    fl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     For
    -0.08
    各项工作
    -0.07
    "For
    -0.07
    doctype
    -0.07
     Mets
    -0.06
     безопасности
    -0.06
    .Serve
    -0.06
    メニュー
    -0.06
     دور
    -0.06
    tk
    -0.06
    POSITIVE LOGITS
    reat
    0.08
    年终
    0.07
     יעל
    0.07
     estado
    0.07
    Contained
    0.07
    ﺨ
    0.06
    /pre
    0.06
    (first
    0.06
    싫
    0.06
    ESH
    0.06
    Act Density 0.005%

    No Known Activations