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

    Neuronpedia

    INDEX
    Explanations

    references to aviation and technical expertise

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

    starting with "con", "pro", or "informa"

    np_acts-logits-general · gemini-2.0-flash

    communication context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     picioare
    -1.02
     viață
    -0.97
     pleaſure
    -0.95
     noastre
    -0.94
     Majefty
    -0.94
     noastră
    -0.91
     argint
    -0.91
     căr
    -0.90
     EconPapers
    -0.89
     acoper
    -0.88
    POSITIVE LOGITS
     con
    0.94
     com
    0.90
     conversa
    0.77
     pro
    0.76
     informa
    0.74
     кото
    0.73
     indepen
    0.73
     momen
    0.72
     persecu
    0.71
     motiva
    0.71
    Act Density 0.195%

    No Known Activations