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

    Neuronpedia

    INDEX
    Explanations

    Hungarian dative/possessive suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    je
    0.66
    ja
    0.65
    jük
    0.57
    جا
    0.54
    је
    0.53
    ju
    0.51
    jay
    0.51
    j
    0.50
    js
    0.49
    jate
    0.49
    POSITIVE LOGITS
     yake
    0.44
    artney
    0.42
    annya
    0.42
     pega
    0.41
    ának
    0.40
     اسے
    0.39
     jego
    0.38
    artan
    0.38
    valo
    0.38
    ONO
    0.38
    Act Density 0.002%

    No Known Activations