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

    Neuronpedia

    INDEX
    Explanations

    .php

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ডিভিশ
    0.40
    Bk
    0.39
    λά
    0.39
     واپسی
    0.38
     Overse
    0.37
    piej
    0.37
     सकुशल
    0.37
    之处
    0.37
     బోర్
    0.36
    <unused17>
    0.36
    POSITIVE LOGITS
     ഉണ്ട
    0.41
     politically
    0.38
    ario
    0.36
    ng
    0.36
    ர்த்த
    0.35
    सान
    0.35
    열
    0.35
     मांगा
    0.34
     keli
    0.34
    اعل
    0.33
    Act Density 0.000%

    No Known Activations