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

    Neuronpedia

    INDEX
    Explanations

    more than just

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Instead
    0.55
     instead
    0.54
     invece
    0.54
     вместо
    0.52
    instead
    0.50
    只需
    0.47
    代わりに
    0.47
    Instead
    0.45
     대신
    0.45
     rather
    0.44
    POSITIVE LOGITS
     includes
    0.48
     encompasses
    0.43
    includes
    0.43
    nH
    0.41
    Kamol
    0.41
    而且
    0.40
    Dimensions
    0.40
    ."'
    0.40
    Includes
    0.38
    Dimensional
    0.38
    Act Density 0.057%

    No Known Activations