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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming functions and definitions

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

    Python type hints and annotations

    np_acts-logits-general · gemini-2.0-flash

    Python type hints and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FromNib
    -0.30
    InitVars
    -0.29
     duplicates
    -0.28
     travel
    -0.28
    放在
    -0.28
     invalid
    -0.28
     bait
    -0.28
     Hag
    -0.27
     parecer
    -0.27
    続きを読む
    -0.27
    POSITIVE LOGITS
    setVerticalGroup
    0.78
    TagMode
    0.66
    AndEndTag
    0.62
     str
    0.62
    tagHelperRunner
    0.61
    str
    0.61
    strate
    0.59
    strates
    0.58
    aarrggbb
    0.58
    Union
    0.56
    Act Density 0.162%

    No Known Activations