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

    Neuronpedia

    INDEX
    Explanations

    timecodes and subtitles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    样的
    0.76
     wider
    0.75
     aw
    0.73
     piling
    0.72
     less
    0.71
     specific
    0.70
     enlarg
    0.70
     document
    0.70
     Toto
    0.70
    最好
    0.69
    POSITIVE LOGITS
     염
    0.86
    肪
    0.73
     운동
    0.73
     Gesture
    0.73
    राजनी
    0.71
    VIDIA
    0.71
     മോ
    0.71
    憨
    0.70
     Inflammation
    0.70
     هم
    0.69
    Act Density 0.001%

    No Known Activations