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

    Neuronpedia

    INDEX
    Explanations

    ending syntax elements in code snippets

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

    Code snippets (likely Javascript or Objective-C)

    np_acts-logits-general · gemini-2.0-flash

    code structure with russian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.64
    ніципа
    -0.62
     law
    -0.62
    SharedDtor
    -0.60
    rungsseite
    -0.58
     single
    -0.58
    saraba
    -0.58
     courriel
    -0.57
    binant
    -0.56
    sizeCache
    -0.55
    POSITIVE LOGITS
    ↵↵↵
    0.57
    клопе
    0.54
    ↵↵↵↵
    0.53
    ↵↵↵↵↵
    0.52
    ↵↵↵↵↵↵
    0.51
    ↵↵↵↵↵↵↵↵↵↵
    0.50
    ↵↵↵↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵↵↵↵↵↵
    0.47
     дописавши
    0.47
    Act Density 0.081%

    No Known Activations