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

    Neuronpedia

    INDEX
    Explanations

    finding things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সমঝো
    0.72
    ьи
    0.71
    ভিন
    0.67
     hopefully
    0.66
     delic
    0.65
     официально
    0.65
     incógn
    0.63
     بمعنى
    0.63
    ভিউ
    0.63
     unknowns
    0.62
    POSITIVE LOGITS
    发现
    3.17
     found
    3.00
     finds
    2.97
    發現
    2.89
     find
    2.83
    Find
    2.72
     Find
    2.70
    find
    2.68
    found
    2.59
     Finds
    2.55
    Act Density 0.111%

    No Known Activations