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

    Neuronpedia

    INDEX
    Explanations

    academic citation numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    सरकार
    0.37
    व्र
    0.36
     primarySwatch
    0.33
     sarkar
    0.31
     গার্ডিয়ান
    0.31
    ەر
    0.30
     compagnies
    0.30
    getPopulation
    0.30
    мии
    0.29
    ？）
    0.29
    POSITIVE LOGITS
    ,
    0.34
     -
    0.31
    -
    0.30
     ...
    0.28
     itself
    0.27
    hist
    0.27
    DE
    0.27
    –
    0.26
    touch
    0.26
    fluss
    0.26
    Act Density 0.000%

    No Known Activations