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

    Neuronpedia

    INDEX
    Explanations

    SQL keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ى
    1.70
    녀
    1.50
    AX
    1.46
    У
    1.42
     Гра
    1.41
     ISZ
    1.41
    SV
    1.39
    И
    1.38
     Signific
    1.37
     AVI
    1.37
    POSITIVE LOGITS
    は何
    1.73
    age
    1.64
    かどうか
    1.64
    lerin
    1.59
     mav
    1.57
    ेंस
    1.55
    ки
    1.52
    ière
    1.46
    はもちろん
    1.46
    ги
    1.45
    Act Density 0.204%

    No Known Activations