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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     or
    -0.48
     and
    -0.43
     individual
    -0.39
     sa
    -0.39
    soort
    -0.38
     chi
    -0.36
     ce
    -0.36
     families
    -0.35
    Descripció
    -0.35
    IDTH
    -0.35
    POSITIVE LOGITS
     could
    0.85
     Normdatei
    0.80
     يتيمه
    0.80
    DoubleQuotes
    0.77
     Bisa
    0.77
     might
    0.77
     Could
    0.76
     būtų
    0.75
    ValueStyle
    0.75
    could
    0.75
    Act Density 0.002%

    No Known Activations