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

    Neuronpedia

    INDEX
    Explanations

    Technical terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <|reserved_200009|>
    -0.18
    <|reserved_200014|>
    -0.18
    ↵
    -0.16
    ↵↵
    -0.16
    <|reserved_200015|>
    -0.16
     天逸
    -0.15
    "↵↵
    -0.15
    `↵
    -0.15
     太阳城
    -0.15
     ↵
    -0.15
    POSITIVE LOGITS
     category
    0.17
     dataset
    0.17
     configuration
    0.16
     component
    0.16
     method
    0.16
     designation
    0.16
     command
    0.16
     scenario
    0.15
     format
    0.15
     system
    0.15
    Act Density 0.467%

    No Known Activations