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

    Neuronpedia

    INDEX
    Explanations

    words used to describe, compare or qualify something as part of a scientific or technical analysis.

    oai_token-act-pair · gemini-2.0-flash

    hard

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.66
     <=",
    -0.60
     Normdatei
    -0.57
     архивлан
    -0.52
     gainera
    -0.50
    NameInMap
    -0.50
    IntoConstraints
    -0.50
     дописавши
    -0.50
    tawesome
    -0.50
    dataflow
    -0.49
    POSITIVE LOGITS
     hard
    3.58
    hard
    3.16
     Hard
    3.13
    Hard
    3.11
     HARD
    2.66
    HARD
    2.59
     harder
    2.17
     hardest
    2.03
     harde
    1.95
     Harder
    1.70
    Act Density 12.672%

    No Known Activations