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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .books
    -0.06
     утеп
    -0.06
     Coord
    -0.06
    .UseText
    -0.06
     StringWriter
    -0.06
    .Dispatcher
    -0.05
     خی
    -0.05
     blackColor
    -0.05
    /downloads
    -0.05
    гот
    -0.05
    POSITIVE LOGITS
    [System
    0.07
    Ÿ
    0.07
     čist
    0.07
    律
    0.07
     побед
    0.06
     honoring
    0.06
     elast
    0.06
    +'"
    0.06
    ¿Â
    0.06
    �
    0.06
    Act Density 0.032%

    No Known Activations