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

    Neuronpedia

    INDEX
    Explanations

    articles/pronouns

    np_max-act · gemini-2.0-flash

    The neuron lightly activates on punctuation and formatting tokens—especially quotation marks and other non‐word symbols.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    GestureRecognizer
    -0.07
     groceries
    -0.07
     Lifecycle
    -0.06
     summarized
    -0.06
    kın
    -0.06
     Dining
    -0.06
     WebSocket
    -0.06
    itone
    -0.06
     filter
    -0.06
    -floor
    -0.06
    POSITIVE LOGITS
    _sess
    0.06
     TOD
    0.06
     profess
    0.06
    col
    0.06
    ίου
    0.06
    pson
    0.06
    Staff
    0.06
    ，是
    0.06
    ccione
    0.06
     pai
    0.06
    Act Density 0.059%

    No Known Activations