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

    Neuronpedia

    INDEX
    Explanations

    Action figures

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of collectible action‐figure products (e.g. “figure,” “figures,” “action figure,” “vintage collection,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    沈
    -0.06
     hj
    -0.06
     عاشق
    -0.06
    /design
    -0.06
    _relation
    -0.06
    Das
    -0.06
     Smoking
    -0.06
    江
    -0.06
     Raised
    -0.05
     dubbed
    -0.05
    POSITIVE LOGITS
     ROUND
    0.07
    �
    0.07
    iddet
    0.07
    ayet
    0.07
    ζει
    0.06
    empt
    0.06
    ;");↵
    0.06
    reachable
    0.06
    ﾆﾆ
    0.06
    rich
    0.06
    Act Density 0.014%

    No Known Activations