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

    Neuronpedia

    INDEX
    Explanations

    patterns related to hierarchical data structures, such as lists and arrays

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

    Code snippets with numbers and brackets

    np_acts-logits-general · gemini-2.0-flash

    shelf numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.72
     Himo
    -0.63
    IsContent
    -0.63
     propOrder
    -0.62
    justed
    -0.59
    EndTag
    -0.54
     JUGA
    -0.54
    cshtml
    -0.53
     wireType
    -0.52
    FundMe
    -0.51
    POSITIVE LOGITS
     whatever
    0.66
    whatever
    0.59
     Whatever
    0.59
    Whatever
    0.57
    AddTagHelper
    0.53
    LEAR
    0.53
     etc
    0.51
    etc
    0.51
    None
    0.50
    IBinder
    0.50
    Act Density 1.029%

    No Known Activations