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

    Neuronpedia

    INDEX
    Explanations

    https://

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    镣
    0.36
     plantas
    0.35
    сант
    0.32
    ‌ന
    0.32
    鎵
    0.32
    ادات
    0.31
     kazan
    0.31
    માન
    0.31
    lovens
    0.31
     piante
    0.31
    POSITIVE LOGITS
     video
    0.49
     Video
    0.46
     GitHub
    0.43
     Github
    0.43
     Pr
    0.41
     Documentation
    0.41
     TODO
    0.40
     Tutorial
    0.40
     DevOps
    0.40
     Dusty
    0.40
    Act Density 0.033%

    No Known Activations