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

    Neuronpedia

    INDEX
    Explanations

    board

    np_max-act · gemini-2.0-flash

    This neuron activates on discussion of a game “board” or grid structure—i.e. when the text is specifying or referring to a 2D board/grid data representation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Jam
    -0.06
     pallet
    -0.06
    chs
    -0.06
     noises
    -0.06
     calf
    -0.06
    obox
    -0.06
    aming
    -0.06
    -chain
    -0.06
     pigeon
    -0.06
    SORT
    -0.06
    POSITIVE LOGITS
     nakne
    0.07
     foundational
    0.07
    (日
    0.07
    predict
    0.07
     numeral
    0.06
     Internacional
    0.06
     KEY
    0.06
    .setObjectName
    0.06
     Christie
    0.06
     CIF
    0.06
    Act Density 0.027%

    No Known Activations