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

    Neuronpedia

    INDEX
    Explanations

    block quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    invisible
    0.40
     ví
    0.38
     leu
    0.38
     invis
    0.37
     zadr
    0.36
     tombol
    0.35
     branding
    0.35
     solu
    0.35
     버튼
    0.35
     invisible
    0.35
    POSITIVE LOGITS
    Quote
    0.65
     quote
    0.63
     quotations
    0.63
    blockquote
    0.62
     quoted
    0.59
     quotation
    0.59
    Zitat
    0.58
    Quotes
    0.57
     Quotes
    0.56
     quotes
    0.56
    Act Density 0.001%

    No Known Activations