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

    Neuronpedia

    INDEX
    Explanations

    references to legal sections or citations in documents

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

    "Section" followed by a bracketed reference

    np_acts-logits-general · gemini-2.0-flash

    section followed by bracketed identifier or Editor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oliven
    -0.54
    Craw
    -0.52
    vatten
    -0.51
    yntaxException
    -0.51
     Gamb
    -0.49
     Flin
    -0.48
    ","+
    -0.48
    whom
    -0.47
     dowry
    -0.47
     Theſe
    -0.47
    POSITIVE LOGITS
     Sections
    1.03
     SECTIONS
    1.01
    Sections
    1.00
     SECTION
    0.95
     Section
    0.92
    SECTION
    0.92
     sections
    0.91
    sections
    0.81
    Section
    0.80
     section
    0.77
    Act Density 0.286%

    No Known Activations