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

    Neuronpedia

    INDEX
    Explanations

    providing examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     అవకాశ
    0.44
     రూప
    0.44
    基本的に
    0.44
    这也是
    0.43
     इनसे
    0.41
     וי
    0.41
     والمت
    0.41
     መሰ
    0.41
    ה
    0.41
     твор
    0.40
    POSITIVE LOGITS
     مثلا
    0.80
     misalnya
    0.75
     například
    0.75
     bijvoorbeeld
    0.74
     mesela
    0.74
     например
    0.70
     például
    0.69
     beispielsweise
    0.62
    例えば
    0.61
    например
    0.61
    Act Density 0.442%

    No Known Activations