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

    Neuronpedia

    INDEX
    Explanations

    references to sections and subsections within a document

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

    section followed by "we"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AttributeSet
    -0.62
     propOrder
    -0.53
    ----</
    -0.51
     defaultstate
    -0.50
     Италијани
    -0.49
     pleaſure
    -0.49
     BrowserModule
    -0.47
     Normdatei
    -0.47
    AutoresizingMask
    -0.45
    styleType
    -0.44
    POSITIVE LOGITS
     intriguing
    0.41
    tagHelperRunner
    0.39
    ➝
    0.38
    RegressionTest
    0.37
     recap
    0.37
     оби
    0.36
     Passo
    0.35
     comparing
    0.35
     Ib
    0.34
     estekak
    0.34
    Act Density 0.170%

    No Known Activations