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

    Neuronpedia

    INDEX
    Explanations

    [modifier] [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     、
    1.15
    丨
    1.14
     adsorption
    1.13
     ℃
    1.11
     丨
    1.06
     deformation
    1.06
     lattices
    1.06
     substances
    1.04
    ostructures
    1.03
     monomers
    1.01
    POSITIVE LOGITS
     präsent
    0.84
    Stats
    0.83
     dành
    0.81
     większość
    0.80
     majorité
    0.77
    有個
    0.75
     ameryka
    0.74
    Legacy
    0.73
     każde
    0.72
     κάπο
    0.72
    Act Density 0.001%

    No Known Activations