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

    Neuronpedia

    INDEX
    Explanations

    common English function words and punctuation, indicating a structure within sentences

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

    "good faith" and "prey"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.49
    postsleuth
    -0.38
     }{@
    -0.36
    tonode
    -0.34
     ReactDOM
    -0.34
    JAKARTA
    -0.34
     Biôgrafia
    -0.32
    ILDREN
    -0.31
     jakim
    -0.31
    Witam
    -0.31
    POSITIVE LOGITS
    ViewImports
    0.62
     noDo
    0.62
     ویکی‌پدی
    0.59
    󠁢
    0.51
     препратки
    0.50
    ंदीखरीदारी
    0.49
     strada
    0.49
    GEBURTSDATUM
    0.48
     bomberos
    0.48
    istoitu
    0.48
    Act Density 0.348%

    No Known Activations