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

    Neuronpedia

    INDEX
    Explanations

    Finnish words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鹛
    0.91
     sporadically
    0.90
     reconsider
    0.89
    льнявыя
    0.88
    UnaryOperation
    0.88
     locomotor
    0.87
    CurrentByte
    0.84
    ObjectUnderTest
    0.84
     biopsies
    0.83
     Thanos
    0.83
    POSITIVE LOGITS
     henkil
    1.24
     pää
    1.20
     tä
    1.14
     yhte
    1.10
     työ
    1.10
     käyt
    1.09
     päiv
    1.09
     vaiht
    1.08
     ympä
    1.08
     suunn
    1.07
    Act Density 0.004%

    No Known Activations