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

    Neuronpedia

    INDEX
    Explanations

    hope it was useful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maybe
    1.31
     MVP
    1.20
     お
    1.19
    嬷
    1.18
     GOT
    1.16
    がいい
    1.15
     Boosting
    1.14
    的話
    1.12
    辙
    1.11
    帮你
    1.11
    POSITIVE LOGITS
     lục
    1.29
     sélectionnez
    1.21
     Vielzahl
    1.18
    정책
    1.17
    PRF
    1.16
    Segments
    1.16
    film
    1.14
    defn
    1.14
     KQkq
    1.14
    θν
    1.12
    Act Density 0.289%

    No Known Activations