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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “work,” especially in contexts like “Our work…” describing research or activities.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .txt
    -0.06
    ัญห
    -0.06
    وجه
    -0.06
    усти
    -0.06
    (factor
    -0.06
    .setScene
    -0.06
     ngọt
    -0.06
     _('
    -0.06
    fang
    -0.06
    configured
    -0.06
    POSITIVE LOGITS
     work
    0.16
     Work
    0.12
     WORK
    0.10
    Work
    0.10
    -work
    0.08
     obra
    0.08
     práce
    0.07
     Alfred
    0.07
     работа
    0.07
     damage
    0.07
    Act Density 0.034%

    No Known Activations