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

    Neuronpedia

    INDEX
    Explanations

    Runnable variable `r` followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     క్యా
    0.47
    實驗
    0.46
    ီ
    0.45
    ার্থী
    0.45
     criança
    0.42
    ін
    0.42
     স্বপ্ন
    0.41
    ه
    0.41
     производи
    0.41
    測試
    0.40
    POSITIVE LOGITS
     Duf
    0.46
    terr
    0.45
     anatom
    0.43
     Bray
    0.42
     Cum
    0.42
     cum
    0.41
     Madeira
    0.41
     dimin
    0.41
     Claro
    0.41
     naal
    0.40
    Act Density 0.000%

    No Known Activations