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

    Neuronpedia

    INDEX
    Explanations

    immediately affect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pintor
    0.46
    鸿
    0.46
     ganador
    0.45
     صفر
    0.45
    टीएम
    0.44
     অভিনেতা
    0.43
    鮨
    0.42
     painter
    0.41
    endidikan
    0.41
    करी
    0.41
    POSITIVE LOGITS
    processing
    0.46
    濡
    0.45
     ئەم
    0.44
     möglichen
    0.44
    dataFile
    0.44
    瀟
    0.44
     هذا
    0.43
    青春
    0.43
     повлия
    0.43
     possíveis
    0.42
    Act Density 0.031%

    No Known Activations