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

    Neuronpedia

    INDEX
    Explanations

    moderate complexity and limitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     context
    0.48
     ambient
    0.45
     fireplace
    0.45
     nursery
    0.45
     in
    0.43
     parquet
    0.43
     names
    0.43
     furniture
    0.43
     pipes
    0.42
     parcels
    0.42
    POSITIVE LOGITS
     плани
    0.54
     असफल
    0.54
     सीमित
    0.52
    できない
    0.50
    谨慎
    0.48
    躊
    0.48
    計画
    0.46
    约束
    0.46
    坚定
    0.46
    计划
    0.45
    Act Density 0.008%

    No Known Activations