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

    Neuronpedia

    INDEX
    Explanations

    double quotes and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    स्‍त
    0.39
    溪
    0.38
    캥
    0.38
    だよ
    0.37
     그려
    0.36
    뭄
    0.36
     repaso
    0.36
     plasmids
    0.36
    ioid
    0.36
     flop
    0.36
    POSITIVE LOGITS
     quote
    3.89
     quotes
    3.83
    Quote
    3.48
     Quote
    3.48
     Quotes
    3.47
     quotation
    3.41
    quote
    3.39
     quotations
    3.38
    quotes
    3.36
    Quotes
    3.34
    Act Density 0.085%

    No Known Activations