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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting elements in text

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

    function call arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.83
    transQ
    -0.60
    RegressionTest
    -0.56
     BoxFit
    -0.56
     AssemblyVersion
    -0.54
     Brewer
    -0.49
     Bioaccumulative
    -0.48
    󠁴
    -0.48
     AssemblyCompany
    -0.48
     OFDb
    -0.48
    POSITIVE LOGITS
    UnsafeEnabled
    0.65
     protoimpl
    0.52
     EconPapers
    0.50
     myſelf
    0.46
     comuniques
    0.44
    MessageState
    0.43
    期刊论文
    0.42
    তথ্যসূত্র
    0.42
     povezave
    0.42
    utilisons
    0.42
    Act Density 0.001%

    No Known Activations