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

    Neuronpedia

    INDEX
    Explanations

    those

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of people involved in wrongdoing (like “victim,” “perpetrator,” “person responsible”) and the consequences or outcomes of harmful actions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     GameController
    -0.06
     Gotham
    -0.06
    Carousel
    -0.06
     चरण
    -0.06
     ebay
    -0.06
     jugg
    -0.06
     Titanic
    -0.06
    ández
    -0.06
    南
    -0.06
    
    -0.06
    POSITIVE LOGITS
     dequeue
    0.06
    люч
    0.06
    .defer
    0.06
     creditor
    0.06
     bei
    0.06
     zav
    0.06
    -navbar
    0.06
    ).(
    0.06
     duy
    0.06
     Opp
    0.06
    Act Density 0.029%

    No Known Activations