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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash

    The neuron detects proper-place names or geographical locations in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Baptist
    -0.07
    .reducer
    -0.07
     inşa
    -0.07
     lại
    -0.07
    azing
    -0.07
     عليها
    -0.06
    alah
    -0.06
     SHARES
    -0.06
    цій
    -0.06
    _UNDEFINED
    -0.06
    POSITIVE LOGITS
     죽
    0.07
    康
    0.06
     Gre
    0.06
    iants
    0.06
    \Json
    0.06
    険
    0.06
     heat
    0.05
    وان
    0.05
     porno
    0.05
     puede
    0.05
    Act Density 0.018%

    No Known Activations