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

    Neuronpedia

    INDEX
    Explanations

    counting items or sequence position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     punten
    0.98
    ième
    0.94
     puluh
    0.88
     días
    0.87
    tenths
    0.85
     décadas
    0.84
    fifths
    0.84
     градусов
    0.82
     theses
    0.82
     dias
    0.82
    POSITIVE LOGITS
    st
    2.58
    xbet
    1.62
    0
    1.50
     st
    1.44
    주일
    1.39
    ️⃣
    1.30
    stArray
    1.29
    ST
    1.25
    хбет
    1.24
    sts
    1.21
    Act Density 0.493%

    No Known Activations