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

    Neuronpedia

    INDEX
    Explanations

    Finding things outdoors

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of discovering a lost object and specifying where it was found.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    items related to lost and found situations, particularly concerning personal belongings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _SCALE
    -0.08
    ye
    -0.07
     twin
    -0.07
    ulant
    -0.06
    dv
    -0.06
    _TOTAL
    -0.06
    Facade
    -0.06
    oreal
    -0.06
    .Objects
    -0.06
    .Init
    -0.06
    POSITIVE LOGITS
     MAIL
    0.07
    反应
    0.06
    _route
    0.06
     Biom
    0.06
    .DataVisualization
    0.06
     actionTypes
    0.06
     banc
    0.06
     Mail
    0.06
     방
    0.06
     yerde
    0.06
    Act Density 0.023%

    No Known Activations