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

    Neuronpedia

    INDEX
    Explanations

    To

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of biological or contagion threats—terms like “biological weapons,” “infect,” “imported cases,” and other disease‐spread language.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gard
    -0.07
     Cape
    -0.06
     Easter
    -0.06
     draft
    -0.06
     मह
    -0.06
     arou
    -0.06
     South
    -0.06
    :",↵
    -0.06
    Tony
    -0.06
    _fm
    -0.06
    POSITIVE LOGITS
    .learn
    0.07
     Lt
    0.06
    .ci
    0.06
    istan
    0.06
    .squareup
    0.06
     chức
    0.06
     mw
    0.06
    _CHAIN
    0.06
     wal
    0.06
     hoog
    0.06
    Act Density 0.145%

    No Known Activations