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

    Neuronpedia

    INDEX
    Explanations

    here is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ataupun
    0.52
    (
    0.52
     ("
    0.51
     участка
    0.50
    .
    0.50
     посредством
    0.49
     metres
    0.48
     jeweiligen
    0.48
     welchen
    0.47
     высокой
    0.47
    POSITIVE LOGITS
     ਹੈ
    0.69
    ಾದರೆ
    0.59
    的事情
    0.54
     پیسې
    0.52
     আছে
    0.51
    厉害
    0.51
    示范
    0.50
    值
    0.50
    ﻓ
    0.50
     ჩატი
    0.49
    Act Density 0.033%

    No Known Activations