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

    Neuronpedia

    INDEX
    Explanations

    Elaboration Likelihood Model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    snake
    -0.09
     snake
    -0.08
     biggest
    -0.08
    Tokyo
    -0.08
     savez
    -0.08
    Snake
    -0.08
     �
    -0.07
     vergangenen
    -0.07
    Lists
    -0.07
     cuáles
    -0.07
    POSITIVE LOGITS
     processing
    0.11
     Verarbeitung
    0.10
    加工
    0.09
     procesamiento
    0.08
    Processing
    0.08
     processamento
    0.08
     Производ
    0.08
    深入
    0.08
    'ép
    0.08
    cription
    0.08
    Act Density 0.006%

    No Known Activations