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

    Neuronpedia

    INDEX
    Explanations

    instances of personal pronouns and related phrases

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

    document section headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FormTagHelper
    -0.38
    IndentedString
    -0.35
    ValueStyle
    -0.34
    InjectAttribute
    -0.33
     fag
    -0.33
     pod
    -0.32
    Autoritní
    -0.31
     Desh
    -0.30
    hashtags
    -0.30
    nehmer
    -0.30
    POSITIVE LOGITS
    !*\
    0.56
    GOTREF
    0.53
     Gemeinsame
    0.52
     campaigned
    0.49
     खरीदा
    0.49
     CreateTagHelper
    0.48
    TagMode
    0.47
     */
    0.47
     EconPapers
    0.46
     reproducible
    0.46
    Act Density 0.017%

    No Known Activations