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

    Neuronpedia

    INDEX
    Explanations

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vorhand
    0.39
     reassuring
    0.39
    proving
    0.38
    copper
    0.38
    reto
    0.38
     sağlay
    0.38
    temperatur
    0.37
    ຶ່ງ
    0.37
     arquivos
    0.36
    coupling
    0.36
    POSITIVE LOGITS
     Tij
    0.38
     ти
    0.38
     ति
    0.38
     Payroll
    0.37
     Profits
    0.37
     المؤ
    0.36
    TikTok
    0.36
    尅
    0.36
     Shen
    0.36
     تط
    0.36
    Act Density 0.003%

    No Known Activations