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

    Neuronpedia

    INDEX
    Explanations

    specific words that are not English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adaptés
    1.27
     동일
    1.21
     गोनी
    1.20
     кожа
    1.19
     inserts
    1.17
    urers
    1.16
     occurrences
    1.16
     endeavours
    1.16
     généraux
    1.14
    銥
    1.14
    POSITIVE LOGITS
    니다
    1.43
    ال
    1.29
    する
    1.24
    دت
    1.20
     bahwa
    1.19
    رك
    1.18
    ため
    1.17
    orus
    1.16
    ва
    1.15
    った
    1.14
    Act Density 0.000%

    No Known Activations