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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens describing a scene of someone seated (e.g. “bench,” “park”)—i.e. it detects when a character is sitting on a bench in a park.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mes
    -0.06
    (wait
    -0.06
     principles
    -0.06
    Wonder
    -0.06
     captivity
    -0.06
     alkal
    -0.06
     explo
    -0.06
     Agility
    -0.06
    creasing
    -0.06
    _pres
    -0.06
    POSITIVE LOGITS
    ::_
    0.07
    _HW
    0.06
    しの
    0.06
     때
    0.06
    μει
    0.06
    stants
    0.06
     desks
    0.06
    >
↵
↵
↵
    0.06
    ندق
    0.06
    aside
    0.06
    Act Density 0.048%

    No Known Activations