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

    Neuronpedia

    INDEX
    Explanations

    statements that emphasize the importance of being mindful or remembering specific information

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

    remembrance or attention

    np_acts-logits-general · gemini-2.0-flash

    keep in mind that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.66
     ControllerBase
    -0.66
    الحياه
    -0.61
    ніципалі
    -0.60
    Personensuche
    -0.60
    ंदीखरीदारी
    -0.59
     ModelExpression
    -0.59
     estekak
    -0.59
     corne
    -0.59
    Jîn
    -0.59
    POSITIVE LOGITS
    要知道
    0.43
    注意
    0.41
     penting
    0.39
    Remember
    0.38
     note
    0.38
    Note
    0.38
     dasarnya
    0.37
    note
    0.36
     Wahrheit
    0.35
    sätzlich
    0.34
    Act Density 0.272%

    No Known Activations