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

    Neuronpedia

    INDEX
    Explanations

    counting two numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ње
    0.40
    ្រ
    0.37
     polyg
    0.37
     dode
    0.35
    ycor
    0.35
    ковь
    0.35
    ведения
    0.35
    ुरु
    0.34
    ورد
    0.34
    қда
    0.34
    POSITIVE LOGITS
     Calculating
    0.52
     possiamo
    0.48
     Again
    0.47
     Luckily
    0.47
    可以使用
    0.46
    我們可以
    0.46
     можно
    0.46
    可以用
    0.46
     podemos
    0.45
     можем
    0.45
    Act Density 0.000%

    No Known Activations