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

    Neuronpedia

    INDEX
    Explanations

    maturity year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inferiores
    0.43
     uses
    0.40
     podataka
    0.39
     regards
    0.39
     alebo
    0.39
    टु
    0.39
    xmlns
    0.39
     naudoj
    0.39
     parámetros
    0.38
     thicker
    0.38
    POSITIVE LOGITS
     народ
    0.42
     Olivia
    0.42
     деле
    0.41
     તમામ
    0.40
     최대한
    0.40
    すべて
    0.40
     сочета
    0.40
     معنات
    0.40
     भावनात्मक
    0.40
     खासियत
    0.40
    Act Density 0.001%

    No Known Activations