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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "wholeness" or completeness in various contexts

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

    entire or whole concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.51
    MemoryWarning
    -0.48
     Darwin
    -0.42
     Oc
    -0.41
     Che
    -0.39
    mod
    -0.39
    pla
    -0.39
     Pen
    -0.39
     Ome
    -0.38
     ARIA
    -0.38
    POSITIVE LOGITS
    整體
    0.63
     totalidad
    0.63
     keseluruhan
    0.61
     ganzes
    0.60
    makeText
    0.57
    whole
    0.55
     orgánico
    0.54
    整体
    0.54
    全体の
    0.52
    égard
    0.52
    Act Density 0.063%

    No Known Activations