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

    Neuronpedia

    INDEX
    Explanations

    key concepts related to origins, motivations, and development processes

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

    cause or origin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.76
    UnusedPrivate
    -0.75
    ंदीखरीदारी
    -0.73
    الإنجليزية
    -0.71
     pinulongan
    -0.71
    OGND
    -0.69
     Taktlose
    -0.66
    NameInMap
    -0.64
    awtextra
    -0.64
    Koordinaten
    -0.63
    POSITIVE LOGITS
     impetus
    0.52
     awalnya
    0.48
     inspiration
    0.44
    きっかけ
    0.44
     Entste
    0.43
     surgiu
    0.43
     inspirado
    0.42
     inspirada
    0.41
     motivation
    0.41
    もとも
    0.40
    Act Density 0.034%

    No Known Activations