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

    Neuronpedia

    INDEX
    Explanations

    Finnish grammatical endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ther
    0.69
    Thor
    0.61
    OW
    0.61
     eg
    0.61
     dimension
    0.61
     wer
    0.58
     f
    0.57
     director
    0.57
     zeit
    0.57
     Ego
    0.57
    POSITIVE LOGITS
    isiin
    1.07
    inen
    1.04
    iseksi
    1.01
    ista
    1.00
    isten
    0.96
    iset
    0.91
    iseen
    0.89
    istaa
    0.85
    iseta
    0.85
    ainen
    0.85
    Act Density 0.002%

    No Known Activations