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

    Neuronpedia

    INDEX
    Explanations

    action movie genres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lysate
    0.49
     humoral
    0.48
     IoT
    0.48
     debugging
    0.47
     수행
    0.47
    racellular
    0.47
     AutoML
    0.46
     photosynthetic
    0.46
     Conductivity
    0.46
     Publishing
    0.45
    POSITIVE LOGITS
     movie
    2.36
    映画
    2.34
     movies
    2.33
     영화
    2.33
     film
    2.20
     films
    2.20
    电影
    2.17
     filme
    2.13
    電影
    2.13
     фильм
    2.13
    Act Density 0.082%

    No Known Activations