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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates primarily on placeholder “NAME_*” tokens (i.e. the anonymized entity name markers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     orderly
    -0.08
    _USER
    -0.07
    .boolean
    -0.06
    _REFRESH
    -0.06
     caffeine
    -0.06
     arrivals
    -0.06
     WLAN
    -0.06
    _fre
    -0.06
     Mondays
    -0.06
    (animation
    -0.06
    POSITIVE LOGITS
     HTMLElement
    0.07
     香港
    0.06
     proj
    0.06
    nesení
    0.06
     Trio
    0.06
     userAgent
    0.06
     sonuç
    0.06
     Fuck
    0.06
     слово
    0.06
    izioni
    0.06
    Act Density 0.115%

    No Known Activations