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

    Neuronpedia

    INDEX
    Explanations

    references to celebrations or commemorative events

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

    celebrate events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MatInputModule
    -0.40
    Map
    -0.39
    ype
    -0.37
    am
    -0.36
     type
    -0.35
    _
    -0.33
    I
    -0.31
     point
    -0.31
     more
    -0.30
    DataSource
    -0.30
    POSITIVE LOGITS
    celebrate
    1.41
    celebr
    1.40
     celebration
    1.39
     celebrate
    1.38
     Celebrate
    1.32
     Celebrations
    1.32
     celebrating
    1.31
    Celebr
    1.31
     celebrations
    1.31
     celebr
    1.30
    Act Density 0.016%

    No Known Activations