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

    Neuronpedia

    INDEX
    Explanations

    repeated references to specific subjects or objects within the text

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

    demonstratives and possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.47
    aarrggbb
    -0.47
    LookAnd
    -0.43
    racuse
    -0.42
    Filmografie
    -0.41
    出版年
    -0.41
     AssemblyVersion
    -0.40
    AndEndTag
    -0.40
    ButtonItem
    -0.39
     calientes
    -0.39
    POSITIVE LOGITS
     ویکی‌پدیا
    0.55
     دیکھیے
    0.45
    ското
    0.42
     terminator
    0.40
    terminator
    0.40
     autorytatywna
    0.40
     BoxFit
    0.40
     Zac
    0.40
    كويكب
    0.39
     Arcadia
    0.39
    Act Density 0.327%

    No Known Activations