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

    Neuronpedia

    INDEX
    Explanations

    hard work

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases that evoke effort or working hard (e.g. “effort,” “put in the work,” “requires”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    emarks
    -0.06
    ugins
    -0.06
    fire
    -0.06
     ("<
    -0.06
     cot
    -0.06
    650
    -0.06
    14
    -0.06
    ordinary
    -0.06
     Iterate
    -0.06
     ig
    -0.06
    POSITIVE LOGITS
    */
↵
↵
    0.07
     pand
    0.06
     nackte
    0.06
    _BUCKET
    0.06
    Consulta
    0.06
    ункт
    0.06
     getUrl
    0.06
     boils
    0.06
    _MISC
    0.06
    aksi
    0.06
    Act Density 0.029%

    No Known Activations