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

    Neuronpedia

    INDEX
    Explanations

    essay writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caching
    0.50
     stickers
    0.44
     playback
    0.44
    ReadLine
    0.43
     Stickers
    0.42
    メンテナンス
    0.42
     headroom
    0.41
    latency
    0.39
     joking
    0.39
     replenishment
    0.39
    POSITIVE LOGITS
     essay
    1.70
     essays
    1.59
     Essay
    1.59
    Essay
    1.47
    essay
    1.45
     Essays
    1.35
     निबंध
    1.24
    论文
    1.19
     thesis
    1.07
    論文
    1.07
    Act Density 0.030%

    No Known Activations