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

    Neuronpedia

    INDEX
    Explanations

    Elizabeth II

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rilev
    0.53
    瞎
    0.51
    ंग
    0.49
     Familia
    0.48
     Обще
    0.46
    CIÓN
    0.46
    ↷
    0.46
    Gü
    0.46
     Фран
    0.45
    Φ
    0.45
    POSITIVE LOGITS
    o
    0.45
    e
    0.43
     trivially
    0.43
     wells
    0.42
     pair
    0.41
     swiftly
    0.40
     spatially
    0.40
    wells
    0.40
    பால
    0.40
     majd
    0.40
    Act Density 0.000%

    No Known Activations