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

    Neuronpedia

    INDEX
    Explanations

    references to ratings or answers within a structured question-and-answer format

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

    Code answers after questions

    np_acts-logits-general · gemini-2.0-flash

    Q&A structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.73
    aarrggbb
    -0.69
    AndEndTag
    -0.66
    الحياه
    -0.65
    MLLoader
    -0.62
     незавершена
    -0.60
    gucig
    -0.59
     Савезне
    -0.58
     ویکی‌پدی
    -0.57
     ſever
    -0.57
    POSITIVE LOGITS
    ：“……”
    0.35
    answer
    0.35
    Wonder
    0.32
    Hm
    0.31
    matter
    0.31
     sm
    0.31
     OMITTED
    0.31
    icoot
    0.30
     (@
    0.30
    发表于
    0.30
    Act Density 0.042%

    No Known Activations