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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and statistical analysis concepts

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

    Section numbering (e.g., 2.2, 3.4)

    np_acts-logits-general · gemini-2.0-flash

    section markers and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.83
    <eos>
    -0.79
    ↵↵
    -0.73
     (
    -0.67
    ↵
    -0.64
     i
    -0.63
      
    -0.60
    ...
    -0.57
     #
    -0.55
    ↵↵↵
    -0.54
    POSITIVE LOGITS
    Datuak
    1.50
    tagHelperRunner
    1.45
    writeFieldEnd
    1.35
     समीक्षाओं
    1.34
    NUMX
    1.32
     ExecuteAsync
    1.27
     ProtoMessage
    1.25
    BibitemShut
    1.25
     ―――――
    1.25
     Chwiliwch
    1.23
    Act Density 0.010%

    No Known Activations