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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GUI
    -0.07
    vil
    -0.07
     walking
    -0.07
     obstacles
    -0.06
     Typeface
    -0.06
     observer
    -0.06
    Caption
    -0.06
    filters
    -0.06
     ल
    -0.06
     bowling
    -0.06
    POSITIVE LOGITS
     ماسه
    0.07
     обычно
    0.06
    goto
    0.06
    اوت
    0.06
     alan
    0.06
    _sync
    0.06
     sonucu
    0.06
     佛
    0.06
     JSBracketAccess
    0.06
     Reef
    0.06
    Act Density 0.038%

    No Known Activations