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

    Neuronpedia

    INDEX
    Explanations

    router, express, and new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     functor
    0.39
     durs
    0.39
     drop
    0.39
    вих
    0.39
     тео
    0.38
     Sod
    0.38
     benchmarks
    0.37
     vow
    0.37
     biore
    0.36
     Антон
    0.36
    POSITIVE LOGITS
    お
    0.46
    orf
    0.42
    Huawei
    0.42
    お知らせ
    0.42
    Police
    0.40
    大
    0.40
    华为
    0.40
    🛵
    0.40
    Router
    0.39
    をお
    0.39
    Act Density 0.002%

    No Known Activations