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

    Neuronpedia

    INDEX
    Explanations

    ChatGPT is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     _$
    0.43
    и
    0.41
    ++;
    0.39
    不会
    0.39
    Sheets
    0.39
    Folder
    0.38
    从
    0.38
    ﻟ
    0.38
     আওয়
    0.38
    pragma
    0.38
    POSITIVE LOGITS
     benessere
    0.46
    grö
    0.46
     paar
    0.45
     የተለያዩ
    0.44
    kond
    0.43
     მაგრამ
    0.43
     ome
    0.43
    兩人
    0.43
    ittle
    0.42
     logotipo
    0.42
    Act Density 0.003%

    No Known Activations