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

    Neuronpedia

    INDEX
    Explanations

    occurrences of backslashes

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

    LaTeX code and math formulas

    np_acts-logits-general · gemini-2.0-flash

    latex mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posedge
    -0.96
     препратки
    -0.88
    queryInterface
    -0.87
    HideFlags
    -0.85
    transQ
    -0.84
    GEBURTSDATUM
    -0.83
    rouvez
    -0.81
     AspNetCore
    -0.79
     propOrder
    -0.78
    Życiorys
    -0.78
    POSITIVE LOGITS
    hline
    0.71
     \
    0.56
    Raw
    0.54
    <tr>
    0.53
     Raw
    0.53
    ron
    0.51
     \\
    0.50
     Υ
    0.50
    0.49
    Pi
    0.48
    Act Density 0.003%

    No Known Activations