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

    Neuronpedia

    INDEX
    Explanations

    references to poetic forms and types in programming contexts

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

    C++ template metaprogramming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.48
    <bos>
    -0.45
    enterOuterAlt
    -0.41
    bootstrapcdn
    -0.41
     seaborn
    -0.40
     تضيفلها
    -0.40
    SourceChecksum
    -0.40
     betweenstory
    -0.40
    ValueStyle
    -0.39
     leisure
    -0.39
    POSITIVE LOGITS
     fanfiction
    0.79
    idosis
    0.64
     fanfic
    0.60
    Kjelder
    0.59
     haiku
    0.57
    ampunk
    0.54
    annotate
    0.51
     dragonfly
    0.51
     shellfish
    0.46
     mussels
    0.45
    Act Density 0.006%

    No Known Activations