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

    Neuronpedia

    INDEX
    Explanations

    Pong game

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “pong,” signaling that it’s detecting mentions of the Pong game.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Pr
    -0.07
     Bordeaux
    -0.06
     Protestant
    -0.06
     jer
    -0.06
    _FRE
    -0.06
    cak
    -0.06
     clo
    -0.06
     판매
    -0.06
     pazar
    -0.06
     Gingrich
    -0.06
    POSITIVE LOGITS
     большой
    0.07
    NavController
    0.07
    0.07
    и
    0.06
    ','.
    0.06
     dapat
    0.06
    getClass
    0.06
     xxxx
    0.06
    .getElementsByTagName
    0.06
    execute
    0.06
    Act Density 0.009%

    No Known Activations