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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of the Earth’s surface (e.g. “surface of the Earth”) in explanatory text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ALL
    -0.06
     �
    -0.06
    /no
    -0.06
    Ford
    -0.06
    _CS
    -0.05
     antes
    -0.05
     kaldı
    -0.05
     yorum
    -0.05
    angs
    -0.05
    علی
    -0.05
    POSITIVE LOGITS
     promises
    0.08
    律
    0.07
     CLI
    0.07
    ->↵
    0.07
     Mei
    0.07
     terrace
    0.07
     fla
    0.07
     gibi
    0.06
     surface
    0.06
     underworld
    0.06
    Act Density 0.013%

    No Known Activations