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

    Neuronpedia

    INDEX
    Explanations

    paper

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of the core rock-paper-scissors game terms, i.e. the move names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lives
    -0.07
    _USED
    -0.06
    혼
    -0.06
    구
    -0.06
     LORD
    -0.06
     evaluated
    -0.06
     TED
    -0.06
     días
    -0.06
    _price
    -0.06
     Lord
    -0.06
    POSITIVE LOGITS
    %)↵↵
    0.08
    この
    0.07
    ="--
    0.06
    prep
    0.06
    primir
    0.06
    Immediately
    0.06
    [child
    0.06
    แกรม
    0.06
    .Abstract
    0.06
                 ↵
    0.06
    Act Density 0.003%

    No Known Activations