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

    Neuronpedia

    INDEX
    Explanations

    Warehouse/factory work

    np_max-act · gemini-2.0-flash

    The neuron lights up on language describing concrete tasks or duties—that is, action-oriented words laying out responsibilities or procedural steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     departments
    -0.07
    ATIONS
    -0.07
    -Z
    -0.07
    *N
    -0.06
    .Comparator
    -0.06
    ointment
    -0.06
     appropriations
    -0.06
    IVES
    -0.06
    -East
    -0.06
    ازل
    -0.06
    POSITIVE LOGITS
     <<-
    0.06
     �
    0.06
    ColumnsMode
    0.06
     EINA
    0.06
     інтер
    0.06
     Garmin
    0.06
     Unblock
    0.06
     "..
    0.06
    etrofit
    0.06
    (pkg
    0.06
    Act Density 0.046%

    No Known Activations