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

    Neuronpedia

    INDEX
    Explanations

    scientific methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    律宾
    -0.08
    .mkdirs
    -0.07
     dolu
    -0.06
    庫
    -0.06
     IRS
    -0.06
     одне
    -0.06
     Bütün
    -0.06
     Ін
    -0.06
     bekan
    -0.06
     виготов
    -0.06
    POSITIVE LOGITS
    .Reporting
    0.07
    械
    0.06
     pace
    0.06
    _lazy
    0.06
     discount
    0.06
    .collection
    0.06
     migrating
    0.06
     engine
    0.06
     engines
    0.06
    гу
    0.06
    Act Density 0.058%

    No Known Activations