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

    Neuronpedia

    INDEX
    Explanations

    academic and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imir
    0.48
    ﹎
    0.47
    Nob
    0.46
    Кра
    0.46
    觫
    0.46
    original
    0.45
    ori
    0.45
    orar
    0.45
    Почему
    0.44
    Какой
    0.44
    POSITIVE LOGITS
     Honest
    0.42
     handouts
    0.41
    至少
    0.40
     evaluating
    0.39
     Vendors
    0.39
     Websites
    0.39
     KPIs
    0.39
     দূ
    0.38
     অনুসারে
    0.38
     medias
    0.38
    Act Density 0.003%

    No Known Activations