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

    Neuronpedia

    INDEX
    Explanations

    famous people's names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    КА
    0.38
    Ciudad
    0.36
     січня
    0.36
     প্রভৃতি
    0.35
    ИТ
    0.35
     ITable
    0.35
     போன்றவை
    0.35
    தியை
    0.34
    RIO
    0.34
    नहीं
    0.34
    POSITIVE LOGITS
     Mr
    0.42
     who
    0.36
     his
    0.35
     দেশ
    0.34
     mr
    0.33
    ského
    0.33
    ભાઇ
    0.33
    ദ്ദേ
    0.32
     Ms
    0.32
    isph
    0.32
    Act Density 0.006%

    No Known Activations