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

    Neuronpedia

    INDEX
    Explanations

    names and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     самые
    0.42
    OW
    0.41
     слабо
    0.40
     пуль
    0.40
     civilians
    0.39
    ז
    0.39
     weakened
    0.39
     cooperate
    0.38
     ক্যামের
    0.38
    ASE
    0.38
    POSITIVE LOGITS
    所谓
    0.54
     Nếu
    0.52
    然后
    0.51
    。"
    0.50
     "!
    0.50
     rồi
    0.49
     whereupon
    0.49
     فاذا
    0.49
     They
    0.48
     ReturnVal
    0.46
    Act Density 0.006%

    No Known Activations