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

    Neuronpedia

    INDEX
    Explanations

    after or exclusive

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ロゴ
    0.56
     パーカー
    0.55
     africa
    0.55
    ApiController
    0.55
     রিপ
    0.54
     leveled
    0.54
    ولوژی
    0.54
    াধ
    0.53
    રે
    0.53
    ardır
    0.53
    POSITIVE LOGITS
     Exclusive
    0.64
     exclusive
    0.63
    exclusive
    0.60
     exclusivity
    0.60
     exclus
    0.57
    premium
    0.56
     précéd
    0.55
     deal
    0.55
     presumption
    0.55
     예
    0.55
    Act Density 0.000%

    No Known Activations