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

    Neuronpedia

    INDEX
    Explanations

    code closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เพียง
    1.59
     gì
    1.55
    TING
    1.50
    𝒂
    1.50
    АТ
    1.40
    ляет
    1.39
    РА
    1.39
    𝗞
    1.39
    𝒉
    1.35
    detailID
    1.34
    POSITIVE LOGITS
    ↵
    2.50
    wdriver
    1.71
    on
    1.68
    ි
    1.67
    ли
    1.55
    g
    1.48
    ection
    1.45
    sburg
    1.43
    sd
    1.41
    años
    1.38
    Act Density 0.259%

    No Known Activations