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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    al
    0.26
    ing
    0.25
    ة
    0.22
    ingin
    0.19
     ।
    0.19
    am
    0.18
    neet
    0.18
    sby
    0.18
    污染物
    0.18
    ă
    0.17
    POSITIVE LOGITS
    そして
    0.23
     பூஜை
    0.21
     फलस्वरूप
    0.21
    Voilà
    0.21
    ༡
    0.20
     prawd
    0.20
     entstehen
    0.20
     appartamento
    0.20
     Architektur
    0.19
     ஸ்ட
    0.19
    Act Density 0.026%

    No Known Activations