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

    Neuronpedia

    INDEX
    Explanations

    best [category] requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
                
    1.25
    ள்ளார்
    1.17
    ﯼ
    1.13
     Вы
    1.10
                    
    1.09
    ENDMENT
    1.09
     supérieurs
    1.09
     polytopes
    1.08
     allemande
    1.08
    1.05
    POSITIVE LOGITS
    ği
    1.48
    owing
    1.38
    خ
    1.35
     यही
    1.30
    sellers
    1.29
    ändig
    1.27
    akse
    1.26
    可以说
    1.23
    ことを
    1.23
     serta
    1.22
    Act Density 0.012%

    No Known Activations