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

    Neuronpedia

    INDEX
    Explanations

    flag

    np_max-act · gemini-2.0-flash

    This neuron detects mentions and descriptions of flags and flag‐related actions (e.g., flag, raised, draped, flown).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     jobs
    -0.07
     advice
    -0.06
     Bard
    -0.06
     veh
    -0.06
     care
    -0.06
     fees
    -0.06
     Hizmet
    -0.06
     Mehmet
    -0.06
    (scan
    -0.06
     separately
    -0.06
    POSITIVE LOGITS
     flag
    0.08
    افة
    0.08
     anthem
    0.08
     Flag
    0.08
    λία
    0.07
    Flag
    0.07
    LError
    0.07
    ні
    0.06
    _aspect
    0.06
     Abb
    0.06
    Act Density 0.007%

    No Known Activations