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

    Neuronpedia

    INDEX
    Explanations

    German, Swedish, and Danish word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DO
    0.67
     Allergy
    0.65
    DO
    0.64
     Aller
    0.64
    Flu
    0.58
     materna
    0.58
     Noir
    0.57
    AAAAAAAA
    0.57
     Byst
    0.56
    zou
    0.56
    POSITIVE LOGITS
    bare
    1.05
    ungen
    0.98
    ning
    0.97
    ende
    0.96
    nings
    0.96
    barkeit
    0.95
    bar
    0.89
    elig
    0.89
    NING
    0.87
    bares
    0.87
    Act Density 0.009%

    No Known Activations