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

    Neuronpedia

    INDEX
    Explanations

    Weak AI or MP main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ブログ
    1.04
     홈페이지
    1.03
    刊
    0.93
     블
    0.91
     재
    0.89
     редак
    0.89
    查看
    0.89
    再現
    0.89
    ಾಸ
    0.88
    スタッフ
    0.87
    POSITIVE LOGITS
    রাতে
    0.90
     Indian
    0.90
    quay
    0.88
     Oswald
    0.87
     Alkali
    0.85
     triglycer
    0.84
    imilar
    0.84
     uninterrupted
    0.84
    igations
    0.83
     indeterminate
    0.83
    Act Density 0.127%

    No Known Activations