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

    Neuronpedia

    INDEX
    Explanations

    purpose improvement and personalization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    婜
    0.42
     ríg
    0.40
    コスト
    0.40
     acceptor
    0.40
     dedos
    0.39
     ඕ
    0.39
     مقاوم
    0.39
     αυτά
    0.38
     diretto
    0.38
     hydrothermal
    0.38
    POSITIVE LOGITS
     services
    0.46
     advertisements
    0.45
    advert
    0.44
     servizi
    0.40
    offer
    0.40
    ayment
    0.39
     service
    0.38
     facilitate
    0.38
     enhance
    0.38
     hizmet
    0.38
    Act Density 0.043%

    No Known Activations