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

    Neuronpedia

    INDEX
    Explanations

    movie titles and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scalability
    0.47
     SaaS
    0.44
     subsystem
    0.44
     infrast
    0.42
     prototyping
    0.42
     langfrist
    0.42
     nutrientes
    0.42
     applicability
    0.42
     solenoid
    0.42
     croissance
    0.42
    POSITIVE LOGITS
     film
    0.90
    映画
    0.87
     फिल्म
    0.86
     영화
    0.84
     фильм
    0.82
    電影
    0.81
     фильме
    0.80
     فیلم
    0.80
     ફિલ્મ
    0.80
    电影
    0.79
    Act Density 0.161%

    No Known Activations