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

    Neuronpedia

    INDEX
    Explanations

    Countries/locations

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of geographic place names (countries, regions, states, provinces, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    irma
    -0.07
     staring
    -0.06
     independence
    -0.06
     cherry
    -0.06
     MPU
    -0.06
    irez
    -0.06
     Burning
    -0.06
    串
    -0.06
    夏
    -0.06
    -component
    -0.06
    POSITIVE LOGITS
    -sem
    0.07
    _UNKNOWN
    0.06
     acres
    0.06
     sinh
    0.06
     rahatsız
    0.06
     electric
    0.06
    _conn
    0.06
    讯
    0.06
    FormGroup
    0.06
    (indexPath
    0.06
    Act Density 0.055%

    No Known Activations