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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    prior
    -0.07
     weekdays
    -0.07
    �
    -0.07
    SBATCH
    -0.07
    lesson
    -0.07
    =[↵
    -0.06
    ><![
    -0.06
     chút
    -0.06
    خی
    -0.06
     Instead
    -0.06
    POSITIVE LOGITS
     foreach
    0.07
     appet
    0.06
     quantidade
    0.06
     empir
    0.06
    ーブ
    0.06
    .ecore
    0.06
    ()?>
    0.06
    avascript
    0.06
    ování
    0.06
     aggrav
    0.05
    Act Density 0.153%

    No Known Activations