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

    Neuronpedia

    INDEX
    Explanations

    concepts related to abstract ideas and reflections

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

    abstract concepts followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.58
    igrette
    -0.47
     cellpadding
    -0.41
     незавершена
    -0.41
     blackout
    -0.41
    <bos>
    -0.41
    pcap
    -0.41
     ratify
    -0.41
    tableLayoutPanel
    -0.41
    PERATURE
    -0.41
    POSITIVE LOGITS
     continúas
    0.47
    transQ
    0.47
    ########.
    0.43
    ագրություններ
    0.41
    devším
    0.40
     âmes
    0.39
    
    0.39
     noten
    0.38
    ″]
    0.37
     nemlig
    0.37
    Act Density 0.657%

    No Known Activations