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

    Neuronpedia

    INDEX
    Explanations

    door

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “garage door” (and its variants like “garage doors”), effectively detecting references to garage‐door services/products.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    interfaces
    -0.07
     Tar
    -0.07
    सम
    -0.06
    “In
    -0.06
    ières
    -0.06
    .loc
    -0.06
     Add
    -0.06
    olds
    -0.06
     Cycling
    -0.06
    :Add
    -0.06
    POSITIVE LOGITS
     Hopkins
    0.06
    Projection
    0.06
    .flush
    0.06
     pilot
    0.06
    %timeout
    0.06
    sizeof
    0.06
    513
    0.06
     persecution
    0.06
     проф
    0.06
    及び
    0.06
    Act Density 0.014%

    No Known Activations