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

    Neuronpedia

    INDEX
    Explanations

    references to articles and academic papers

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

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.49
     Vikipedi
    -0.44
    diad
    -0.40
    CIL
    -0.40
    lccc
    -0.39
     ModelRenderer
    -0.39
     дописавши
    -0.39
     Zwie
    -0.39
     Lightboxes
    -0.38
    EEA
    -0.37
    POSITIVE LOGITS
    ArgsConstructor
    0.58
    BeginInit
    0.58
    enumi
    0.54
    BufferException
    0.50
    帖最后由
    0.49
    先日
    0.45
     propOrder
    0.43
     recently
    0.43
    来歴
    0.42
     recientemente
    0.40
    Act Density 0.006%

    No Known Activations