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

    Neuronpedia

    INDEX
    Explanations

    markup or structured data elements within code

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

    Tokens preceding type="text/javascript" or similar

    np_acts-logits-general · gemini-2.0-flash

    text followed by /

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.94
    __":
    -0.90
     BorderRadius
    -0.87
    windowFixed
    -0.87
    脚注の使い方
    -0.85
    __':
    -0.84
     تانيه
    -0.82
     NSCoder
    -0.79
    Билгалдахарш
    -0.79
    таратура
    -0.74
    POSITIVE LOGITS
    /
    1.56
    \/
    1.31
    ／
    1.29
     /
    1.22
    ⁄
    1.11
    ∕
    1.08
    /{
    0.97
    /}{
    0.94
    /\
    0.93
    /${
    0.91
    Act Density 0.575%

    No Known Activations