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

    Neuronpedia

    INDEX
    Explanations

    strangers

    np_max-act · gemini-2.0-flash

    This neuron fires strongly on mentions of “strangers” (and related contexts of encountering or interacting with unknown people).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     opcion
    -0.07
     corrupt
    -0.07
     Thái
    -0.07
     एव
    -0.07
     centro
    -0.06
     Christmas
    -0.06
    Gay
    -0.06
     amo
    -0.06
    陳
    -0.06
     Houses
    -0.06
    POSITIVE LOGITS
     DDR
    0.07
    assertInstanceOf
    0.06
     descon
    0.06
     stranger
    0.06
    abling
    0.06
    omore
    0.06
     strangers
    0.06
    .By
    0.06
    _STYLE
    0.06
    (bodyParser
    0.06
    Act Density 0.019%

    No Known Activations