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

    Neuronpedia

    INDEX
    Explanations

    articles and information sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     niezbęd
    0.79
    大切な
    0.75
    自由に
    0.72
    morale
    0.71
     voorzien
    0.70
    iapkan
    0.68
     précieux
    0.68
    <unused443>
    0.68
    ujemy
    0.67
    becomes
    0.67
    POSITIVE LOGITS
     article
    2.48
     articles
    2.13
    的文章
    2.01
     artikel
    1.99
     Wikipedia
    1.94
    の記事
    1.94
     wikipedia
    1.92
     artikkel
    1.92
     videos
    1.86
     youtube
    1.85
    Act Density 0.169%

    No Known Activations