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

    Neuronpedia

    INDEX
    Explanations

    unless specifically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dù
    0.49
     ليس
    0.49
     любом
    0.48
     ANY
    0.45
     Any
    0.44
     qualsiasi
    0.43
    即使
    0.43
    どれ
    0.42
     qualquer
    0.42
     любого
    0.42
    POSITIVE LOGITS
     expressly
    1.12
     specifically
    1.05
     absolutely
    0.97
    specifically
    0.93
     специально
    0.90
    Specifically
    0.89
     explicitly
    0.89
     específicamente
    0.87
    absolutely
    0.84
    Absolutely
    0.84
    Act Density 0.012%

    No Known Activations