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

    Neuronpedia

    INDEX
    Explanations

    the fundamental concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ınızı
    0.44
    ুপ্ত
    0.41
    ალა
    0.41
    িকালে
    0.40
    মতি
    0.39
     زاده
    0.39
    之下
    0.38
     توانید
    0.38
    结束后
    0.38
     kuhusu
    0.37
    POSITIVE LOGITS
     beinh
    0.52
     basic
    0.48
     الأساس
    0.47
     基本
    0.47
     기본적인
    0.47
     శరీర
    0.45
     überhaupt
    0.44
     základ
    0.43
    湇
    0.43
     defini
    0.43
    Act Density 0.003%

    No Known Activations