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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash

    The neuron activates on verbs indicating an athletic playing career (e.g., “played,” “playing,” “plays”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Acc
    -0.07
    .Rec
    -0.07
    fund
    -0.06
    woord
    -0.06
    ,NULL
    -0.06
     screenplay
    -0.06
    ~":"
    -0.06
    {T
    -0.06
    [cell
    -0.06
    );$
    -0.06
    POSITIVE LOGITS
     played
    0.07
    avity
    0.07
    ulsion
    0.07
    醴
    0.06
     Played
    0.06
     pal
    0.06
    164
    0.06
     Dominion
    0.06
     gastro
    0.06
     quick
    0.06
    Act Density 0.009%

    No Known Activations