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

    Neuronpedia

    INDEX
    Explanations

    concepts related to knowledge, certainty, and decision-making

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

    impossible to know whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actionPerformed
    -0.59
    useNewUrlParser
    -0.47
    CardHeader
    -0.47
    PCell
    -0.47
    ########.
    -0.47
     snippetHide
    -0.46
    WaitGroup
    -0.44
     repul
    -0.43
    Bib
    -0.43
     UIAlert
    -0.43
    POSITIVE LOGITS
    aarrggbb
    0.44
    不知道
    0.37
    ValueStyle
    0.36
     sappiamo
    0.36
    setVerticalGroup
    0.35
     sabemos
    0.35
     duele
    0.35
    ActionCreators
    0.35
    AccessorTable
    0.35
     iNdEx
    0.34
    Act Density 0.160%

    No Known Activations