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

    Neuronpedia

    INDEX
    Explanations

    mill words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ми
    0.94
     Mustangs
    0.87
     bouquets
    0.75
     Mondays
    0.74
     showers
    0.73
     глаз
    0.73
     Pastel
    0.72
     MIR
    0.71
     leçon
    0.70
     Ми
    0.70
    POSITIVE LOGITS
    ennium
    1.18
    imetre
    1.17
    enium
    1.14
    imeter
    1.13
    ennia
    1.11
    imeters
    1.03
    enni
    0.98
    iners
    0.98
    iken
    0.98
    race
    0.98
    Act Density 0.003%

    No Known Activations