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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reading and enjoyment of books

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

    already done or repeat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.48
    较为
    -0.46
    UnsafeEnabled
    -0.45
     Biôgrafia
    -0.44
    Decent
    -0.44
    UnknownFields
    -0.42
    ]")]
    -0.41
     nogen
    -0.40
     enfans
    -0.38
     pstmt
    -0.37
    POSITIVE LOGITS
     repeat
    0.68
     already
    0.60
     repeats
    0.58
     Already
    0.58
     ASAP
    0.57
     asap
    0.56
    Already
    0.56
     ALREADY
    0.55
     Repeat
    0.55
    already
    0.55
    Act Density 0.018%

    No Known Activations