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

    Neuronpedia

    INDEX
    Explanations

    Single-digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _faces
    -0.07
     Accum
    -0.06
    	main
    -0.06
    Comment
    -0.06
    [left
    -0.06
     Cruc
    -0.06
    .album
    -0.06
    ANGED
    -0.06
    "Some
    -0.06
    iationException
    -0.06
    POSITIVE LOGITS
     tucked
    0.08
    pagesize
    0.07
     nicer
    0.07
    ilerinin
    0.06
    eyle
    0.06
     initializes
    0.06
     ",
    0.06
    臺灣
    0.06
     kurtar
    0.06
    –and
    0.06
    Act Density 0.043%

    No Known Activations