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

    Neuronpedia

    INDEX
    Explanations

    numeric expressions that indicate significant amounts or measurements.

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

    Code snippets and HTML tags

    np_acts-logits-general · gemini-2.0-flash

    html and xml closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Waray
    -0.75
     noqa
    -0.66
    __':
    -0.65
    abetes
    -0.65
    !*\
    -0.64
     lenker
    -0.61
    Viitteet
    -0.61
     ProtoMessage
    -0.61
     MainAxisSize
    -0.59
    istoitu
    -0.58
    POSITIVE LOGITS
    <eos>
    2.24
    <unused60>
    1.14
    <unused63>
    1.11
    <unused61>
    1.04
    </i>
    0.72
    </em>
    0.70
    </u>
    0.66
    </code>
    0.65
    </s>
    0.60
    </blockquote>
    0.55
    Act Density 0.419%

    No Known Activations