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

    Neuronpedia

    INDEX
    Explanations

    ranked resumes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আগে
    0.47
    сей
    0.47
     є
    0.46
     nào
    0.46
     stratification
    0.45
    ὃ
    0.45
     Mocha
    0.44
    ς
    0.44
     কমপ্লে
    0.43
     кода
    0.43
    POSITIVE LOGITS
     gren
    0.42
     teie
    0.42
     uud
    0.41
    m
    0.40
     gill
    0.40
     svog
    0.40
    aan
    0.39
     नारी
    0.39
    ভূত
    0.38
    უშ
    0.38
    Act Density 0.001%

    No Known Activations