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

    Neuronpedia

    INDEX
    Explanations

    column names and fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pastor
    0.46
    Pastor
    0.42
     Michelin
    0.40
     estado
    0.40
    窯
    0.40
     aparato
    0.40
     batches
    0.38
     wafers
    0.38
    لون
    0.38
     pastries
    0.38
    POSITIVE LOGITS
     columns
    0.63
     Columns
    0.62
     fields
    0.61
     ColumnName
    0.61
    字段
    0.59
    columns
    0.59
     column
    0.56
     variables
    0.54
    Columns
    0.53
    列
    0.52
    Act Density 0.263%

    No Known Activations