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

    Neuronpedia

    INDEX
    Explanations

    words relating to MX racing and the WMA

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -0.75
     propOrder
    -0.65
    ContentAsync
    -0.62
    antaranya
    -0.58
    UnusedPrivate
    -0.57
     InputDecoration
    -0.56
    StoryboardSegue
    -0.55
    laken
    -0.54
     consultato
    -0.54
    PerformLayout
    -0.54
    POSITIVE LOGITS
    وردار
    0.60
     carpenters
    0.50
    cryption
    0.47
     skates
    0.47
    بوابة
    0.47
     sahiptir
    0.46
     Velázquez
    0.46
     geothermal
    0.46
     prostitute
    0.46
    BITDA
    0.45
    Act Density 3.076%

    No Known Activations