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

    Neuronpedia

    INDEX
    Explanations

    code snippets and functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     would
    0.58
     may
    0.54
    may
    0.52
     sometime
    0.51
     might
    0.51
    would
    0.51
     wäre
    0.50
     இருக்கலாம்
    0.50
     tending
    0.49
     perhaps
    0.45
    POSITIVE LOGITS
     Функция
    0.76
     ánh
    0.72
    และการ
    0.69
    调用
    0.68
     زیبایی
    0.66
     بررسی
    0.66
     funcao
    0.65
    函数
    0.64
    采用
    0.63
    函數
    0.63
    Act Density 2.111%

    No Known Activations