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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting in textual representations, particularly in the context of data analysis or programming scripts

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

    LaTeX math formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.47
     CURLOPT
    -0.42
     MainAxisSize
    -0.40
     useRouter
    -0.40
    ruik
    -0.39
    ransition
    -0.39
    fürst
    -0.37
     Routing
    -0.36
    fony
    -0.36
    urto
    -0.36
    POSITIVE LOGITS
     mitään
    0.58
     aikaa
    0.52
    +#+#
    0.48
     ujednoznacz
    0.47
    :✨
    0.46
     operazioni
    0.45
    preuves
    0.44
    domada
    0.44
     enää
    0.43
    webElementXpaths
    0.43
    Act Density 0.618%

    No Known Activations