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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and coding syntax

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

    Code or bracket sequences

    np_acts-logits-general · gemini-2.0-flash

    indexing lists and tuples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eighth
    -0.68
     seventh
    -0.63
     seventy
    -0.61
     eighty
    -0.61
     sixty
    -0.61
     seven
    -0.59
    Six
    -0.59
     Seventy
    -0.58
     noDo
    -0.58
     eight
    -0.57
    POSITIVE LOGITS
    XmlAccessType
    0.72
    rawDesc
    0.68
     resourceCulture
    0.62
    verifyException
    0.60
    脚注の使い方
    0.57
    Przypisy
    0.56
     дописавши
    0.54
    awaiter
    0.54
     autorytatywna
    0.53
    yntaxException
    0.51
    Act Density 0.138%

    No Known Activations