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

    Neuronpedia

    INDEX
    Explanations

    native speakers or languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ال
    2.19
    نا
    2.14
     infographics
    2.11
    ى
    2.08
    म
    2.06
    س
    2.03
    ونم
    1.99
    ें
    1.94
    ियों
    1.86
    िन
    1.85
    POSITIVE LOGITS
     volna
    2.30
     Τα
    2.16
    compound
    1.87
     quidem
    1.80
    cl
    1.75
    こと
    1.75
    command
    1.71
    islav
    1.70
    comb
    1.70
    {~
    1.69
    Act Density 0.013%

    No Known Activations