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

    Neuronpedia

    INDEX
    Explanations

    geographic regions

    np_max-act · gemini-2.0-flash

    The neuron detects words related to geographic scope or regional settings (e.g., “global,” “regional,” “local,” “circumvent restrictions”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iations
    -0.06
     Discover
    -0.06
     อย
    -0.06
     Kardashian
    -0.06
    lav
    -0.06
    شتر
    -0.06
     burge
    -0.06
    arsity
    -0.06
     Lect
    -0.06
     sie
    -0.05
    POSITIVE LOGITS
     QE
    0.07
    PCM
    0.07
     (_
    0.07
    _TAG
    0.07
    clinical
    0.07
    neo
    0.07
     SNMP
    0.06
    -regexp
    0.06
    callee
    0.06
    _AL
    0.06
    Act Density 0.037%

    No Known Activations