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

    Neuronpedia

    INDEX
    Explanations

    references to documentation summaries or sections

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that are part of named entities or technical/proper nouns (e.g., titles, model or disease names).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.63
    NameInMap
    -0.60
    MigrationBuilder
    -0.59
    Personendaten
    -0.59
     snippetHide
    -0.58
     Савезне
    -0.57
     tartalomajánló
    -0.54
     wireType
    -0.53
     ***!
    -0.53
     незавершена
    -0.52
    POSITIVE LOGITS
     mutiara
    0.47
     scatt
    0.45
     pierna
    0.45
     braço
    0.44
     braços
    0.42
    hộp
    0.42
     rodilla
    0.42
     prisa
    0.41
    อ้าง
    0.41
     comiendo
    0.40
    Act Density 0.000%

    No Known Activations