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

    Neuronpedia

    INDEX
    Explanations

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ribusi
    0.28
    Vas
    0.27
    ỹ
    0.26
     ৭৭
    0.26
     vasodil
    0.25
     задачу
    0.25
     রব
    0.25
     discoloration
    0.24
    ITATE
    0.24
     Vas
    0.24
    POSITIVE LOGITS
     ۲۰
    0.38
     ۱۰
    0.38
    十几
    0.36
     ১৫
    0.35
     ۱۵
    0.34
    ５
    0.33
    ۱۰
    0.31
     dozen
    0.31
    5
    0.30
     fifteen
    0.30
    Act Density 0.047%

    No Known Activations