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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

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

    thanks, sincerely, or you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -1.03
    ValueStyle
    -1.00
     يتيمه
    -0.98
     Italijani
    -0.93
    webElementXpaths
    -0.91
    GEBURTSDATUM
    -0.87
     kasarigan
    -0.85
     lenker
    -0.83
     podjela
    -0.81
     Meksiku
    -0.80
    POSITIVE LOGITS
    S
    0.29
     Freiheit
    0.28
    l
    0.27
    Me
    0.27
    Post
    0.26
    Autowired
    0.26
    🏻
    0.26
     Royaume
    0.26
    Path
    0.26
    I
    0.26
    Act Density 0.004%

    No Known Activations