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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and parentheses, highlighting a focus on syntax and structure in text

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

    following parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.42
    abrigo
    -0.40
     LIRE
    -0.37
     ivelany
    -0.36
    ToLeft
    -0.35
    uxxxx
    -0.35
     récla
    -0.35
    Personensuche
    -0.33
     CreateTagHelper
    -0.33
    +#+#
    -0.33
    POSITIVE LOGITS
     ujednoznacz
    0.62
    Personendaten
    0.62
    saraba
    0.61
    évaluateur
    0.56
     pleaſure
    0.55
     IBOutlet
    0.54
     Bhattach
    0.54
    webElementXpaths
    0.54
    naphthal
    0.52
    FirebaseDatabase
    0.50
    Act Density 0.219%

    No Known Activations