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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "work" in varying contexts

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     work
    -2.44
    Work
    -2.20
     Work
    -2.17
    work
    -2.11
     WORK
    -1.95
    WORK
    -1.83
     Arbeit
    -1.58
     trabajo
    -1.52
    工作
    -1.45
     lavoro
    -1.45
    POSITIVE LOGITS
     autorytatywna
    0.96
    tagext
    0.88
    rungsseite
    0.79
     ivelany
    0.77
    UserScript
    0.76
     GenerationType
    0.75
    Portale
    0.75
    XmlAccessType
    0.73
    tvguidetime
    0.72
    Tembelea
    0.70
    Act Density 0.404%

    No Known Activations