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

    Neuronpedia

    INDEX
    Explanations

    programming function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     เมือง
    0.38
     сейчас
    0.36
    रावती
    0.36
     Сейчас
    0.35
     물질
    0.35
     હજાર
    0.35
    োস
    0.35
    перыі
    0.35
    പ്പെട
    0.34
     нови
    0.34
    POSITIVE LOGITS
    函数
    0.78
     function
    0.75
    函數
    0.72
    関数
    0.66
     func
    0.64
     함수
    0.63
     функция
    0.62
     functions
    0.59
    function
    0.58
    函数的
    0.57
    Act Density 0.432%

    No Known Activations