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

    Neuronpedia

    INDEX
    Explanations

    list of letters, words, or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మేరకు
    0.36
     HEN
    0.36
    ড়ার
    0.35
     automaker
    0.35
     Blossom
    0.31
    ಪೆ
    0.31
     त्यांची
    0.31
    攢
    0.31
     човек
    0.31
     Олександр
    0.31
    POSITIVE LOGITS
    zni
    0.36
    wu
    0.31
    upid
    0.30
    zieh
    0.30
     benda
    0.29
    Slave
    0.29
     bhakti
    0.29
    celer
    0.28
    Qt
    0.27
    Bins
    0.27
    Act Density 0.006%

    No Known Activations