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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    poses
    -0.08
    мента
    -0.07
     Het
    -0.06
     MODE
    -0.06
    .RGB
    -0.06
     ماه
    -0.06
    odí
    -0.06
    較
    -0.06
    #
    -0.06
     Mann
    -0.06
    POSITIVE LOGITS
    _inc
    0.08
     include
    0.08
    _INCLUDED
    0.07
    	include
    0.07
    include
    0.07
    Includes
    0.07
    Include
    0.07
    essian
    0.07
     hone
    0.07
    <span
    0.06
    Act Density 0.051%

    No Known Activations