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

    Neuronpedia

    INDEX
    Explanations

    forgetting

    np_max-act · gemini-2.0-flash

    instances where someone doesn't notice something or someone.

    oai_token-act-pair · gpt-4oTriggered by @tcai

    the main thing this neuron does is detect mentions of awareness or perception—particularly when the text describes noticing (or failing to notice) events or the passage of time.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms related to playful or mischievous activities involving balloons.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    世界
    -0.07
    力量
    -0.06
    've
    -0.06
    AS
    -0.06
    _REFRESH
    -0.06
    _reservation
    -0.06
    IfNeeded
    -0.06
    儀
    -0.06
    Await
    -0.06
    feld
    -0.06
    POSITIVE LOGITS
    mult
    0.07
     PowerShell
    0.07
    すれば
    0.06
    onedDateTime
    0.06
    主题
    0.06
    .hours
    0.06
     Katrina
    0.06
     BrowserModule
    0.06
     QMap
    0.06
    *X
    0.06
    Act Density 0.014%

    No Known Activations