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

    Neuronpedia

    INDEX
    Explanations

    the word "progress"

    oai_token-act-pair · gemini-2.0-flash

    progress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagMode
    -1.17
    RenderAtEndOf
    -0.96
      (
    -0.93
     digress
    -0.92
    ########.
    -0.91
    enumii
    -0.88
    XmlAccessType
    -0.87
    存于互联网档案馆
    -0.86
    WebVitals
    -0.85
    المناصب
    -0.85
    POSITIVE LOGITS
    s
    0.88
    t
    0.74
    k
    0.67
    a
    0.65
    .
    0.63
    ↵
    0.62
    d
    0.61
     
    0.60
    ers
    0.59
    ↵↵
    0.57
    Act Density 1.430%

    No Known Activations