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

    Neuronpedia

    INDEX
    Explanations

    damage

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of damage or harm (words like “damage,” “vehicles,” “injuries,” etc.) in accident reports.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Talent
    -0.07
    Opening
    -0.07
    capacity
    -0.07
    bia
    -0.07
     بد
    -0.07
     サ
    -0.07
     Manager
    -0.06
    .CreateTable
    -0.06
     qualifications
    -0.06
    Senior
    -0.06
    POSITIVE LOGITS
     khuyến
    0.06
     пы
    0.06
     photoshop
    0.06
    �
    0.06
    ","
    0.06
    시는
    0.06
    rogram
    0.06
    WINDOWS
    0.06
    /info
    0.06
    .bio
    0.06
    Act Density 0.016%

    No Known Activations