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

    Neuronpedia

    INDEX
    Explanations

    prepositions in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ó
    2.44
    na
    2.42
    İN
    2.39
     fibroblasts
    2.30
    它
    2.30
    𝐢
    2.27
    𝐥
    2.20
    ität
    2.13
    ک
    2.06
    یان
    2.03
    POSITIVE LOGITS
    тический
    2.25
    тические
    2.16
     umumnya
    2.11
    тику
    2.08
    последствии
    1.99
    тическая
    1.96
    ю
    1.96
    ن
    1.95
    ication
    1.92
    тике
    1.91
    Act Density 0.003%

    No Known Activations