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

    Neuronpedia

    INDEX
    Explanations

    non-english text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     News
    0.90
    News
    0.88
     news
    0.78
    Trending
    0.76
    news
    0.75
     newsc
    0.75
     নিউজ
    0.75
    Ticker
    0.74
     Today
    0.73
    更新
    0.71
    POSITIVE LOGITS
     pharmacies
    0.93
    햇
    0.92
     polyester
    0.90
     கொண்டிருந்த
    0.88
     Bibliothèque
    0.88
    ोदर
    0.86
     PU
    0.84
     artefact
    0.82
     cheeks
    0.82
     monogram
    0.81
    Act Density 0.004%

    No Known Activations