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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and empty spaces in code snippets

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

    `<start_of_turn> user`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     once
    -0.41
     if
    -0.39
     by
    -0.38
     nobody
    -0.38
     past
    -0.38
     after
    -0.36
     unless
    -0.36
     federal
    -0.34
     beyond
    -0.33
     from
    -0.33
    POSITIVE LOGITS
     مرئيه
    0.73
    IContainer
    0.70
     nakalista
    0.66
    WithIOException
    0.64
     Administrativna
    0.62
    webElementXpaths
    0.61
     propOrder
    0.60
    StoreMessageInfo
    0.60
    __":
    0.60
    adaptiveStyles
    0.60
    Act Density 0.001%

    No Known Activations