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

    Neuronpedia

    INDEX
    Explanations

    occurrences of mathematical or scientific notation elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML tables and math equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.49
    windowFixed
    -0.48
     simula
    -0.45
     Persson
    -0.45
     Sándor
    -0.42
     betweenstory
    -0.41
    ity
    -0.41
     Henning
    -0.40
    ware
    -0.39
     Nowak
    -0.39
    POSITIVE LOGITS
    td
    0.81
    httphttps
    0.71
     تضيفلها
    0.69
    HtmlAttribute
    0.60
    ReusableCell
    0.59
     nahilalakip
    0.57
    \{\\
    0.57
    CodeAttribute
    0.57
    AnchorStyles
    0.56
    MLLoader
    0.56
    Act Density 0.001%

    No Known Activations