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

    Neuronpedia

    INDEX
    Explanations

    Program

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Moist
    -0.07
     mushroom
    -0.07
     Kensington
    -0.07
     Jahres
    -0.07
     spice
    -0.06
     chef
    -0.06
    _squared
    -0.06
     stamp
    -0.06
     Bund
    -0.06
     Beginner
    -0.06
    POSITIVE LOGITS
    ordinal
    0.07
    |{↵
    0.07
    [sub
    0.06
     эксплуата
    0.06
    horizontal
    0.06
    ("\"
    0.06
    [Unit
    0.06
    dims
    0.06
     Plaint
    0.06
     giá
    0.06
    Act Density 0.001%

    No Known Activations