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

    Neuronpedia

    INDEX
    Explanations

    code blocks and programming context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oficiais
    0.46
     Ferrari
    0.45
    完美的
    0.44
     funcionando
    0.43
     funcionamento
    0.41
     quello
    0.40
     clube
    0.40
    ieres
    0.39
     Guard
    0.39
    执行
    0.39
    POSITIVE LOGITS
    پن
    0.52
     δημ
    0.51
    thyl
    0.49
     ਪ੍ਰ
    0.49
    syair
    0.48
     próp
    0.46
     magni
    0.44
     больш
    0.44
     کردم
    0.44
    тию
    0.43
    Act Density 0.001%

    No Known Activations