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

    Neuronpedia

    INDEX
    Explanations

    phrases involving prepositions and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ene
    0.50
    ens
    0.45
     ነገር
    0.45
     ඉතා
    0.44
    ღვ
    0.43
     ओह
    0.43
     oligodend
    0.42
    েরিক
    0.42
     contrats
    0.42
    iter
    0.41
    POSITIVE LOGITS
    тия
    0.50
     kanyang
    0.47
     Prasad
    0.45
     осо
    0.43
     yandan
    0.42
    жения
    0.39
    UO
    0.39
    гда
    0.39
     લાભ
    0.38
     sua
    0.38
    Act Density 0.002%

    No Known Activations