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

    Neuronpedia

    INDEX
    Explanations

    news articles and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yapıyor
    0.40
     फौज
    0.40
     بیمار
    0.38
    他又
    0.37
    fü
    0.36
    cyclic
    0.36
     vä
    0.35
    animate
    0.35
    isNaN
    0.35
     PIB
    0.35
    POSITIVE LOGITS
     storyline
    0.45
     journalistic
    0.41
     Story
    0.39
    мам
    0.39
     लोका
    0.38
     Ive
    0.37
     story
    0.37
     tinta
    0.37
    uary
    0.37
     স্বপ
    0.37
    Act Density 0.000%

    No Known Activations