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

    Neuronpedia

    INDEX
    Explanations

    bans

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of immigration-related terms (visas, refugees, applicants, immigrants) and specific country names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    blank
    -0.07
     bert
    -0.07
    اها
    -0.06
    Maintenance
    -0.06
     mash
    -0.06
     خلف
    -0.06
    .staff
    -0.06
    小
    -0.06
    _gray
    -0.06
    Merit
    -0.06
    POSITIVE LOGITS
    -sizing
    0.06
     intrinsic
    0.06
     Missile
    0.06
     fprintf
    0.06
     jur
    0.06
    리에
    0.06
     Edison
    0.06
    辰
    0.06
    .confirm
    0.06
     Chem
    0.06
    Act Density 0.021%

    No Known Activations