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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ("",
    0.19
     আচ্ছা
    0.18
     নিয়োগ
    0.18
     ചേർ
    0.18
     চার
    0.17
     تنا
    0.17
     తో
    0.17
     ശ്രദ്ധ
    0.17
     зачем
    0.17
     考え
    0.17
    POSITIVE LOGITS
    %
    0.37
    0
    0.34
     million
    0.33
    %,
    0.32
    kHz
    0.31
     kHz
    0.30
    km
    0.30
    th
    0.30
     percent
    0.30
     dollars
    0.30
    Act Density 0.166%

    No Known Activations