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

    Neuronpedia

    INDEX
    Explanations

    roles and entities in communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    து
    1.22
    ся
    1.18
    1.03
    তা
    1.03
    ী
    1.02
    ्ज
    0.98
    ure
    0.98
     ficar
    0.97
     स्थिति
    0.97
     возле
    0.96
    POSITIVE LOGITS
    {-#
    0.91
     lucrative
    0.89
    in
    0.89
    {}
    0.88
    }}^{\
    0.85
    हेही
    0.85
    ל
    0.83
    ől
    0.82
     Canad
    0.82
     आरमारा
    0.81
    Act Density 0.046%

    No Known Activations