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

    Neuronpedia

    INDEX
    Explanations

    fluorescence, filter, sales, content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     axisymmetric
    0.41
    릉
    0.41
     норм
    0.41
    ابات
    0.40
     যন্ত্রপাতি
    0.39
    ጶ
    0.39
    .’’
    0.38
    नाडु
    0.38
     சித்தர்
    0.38
    환경
    0.37
    POSITIVE LOGITS
    read
    0.58
     read
    0.51
     table
    0.43
    Read
    0.43
    jar
    0.42
    ija
    0.42
     reading
    0.41
     Sentinel
    0.40
    table
    0.40
    sed
    0.40
    Act Density 0.000%

    No Known Activations