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
    *))
    -0.08
     Pax
    -0.08
    parsers
    -0.07
    Authorization
    -0.07
    _battery
    -0.07
     Woodward
    -0.07
    	fprintf
    -0.07
    -shift
    -0.07
    308
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     included
    0.08
    क
    0.07
     inclusion
    0.07
    .addColumn
    0.07
     scholar
    0.07
    bilt
    0.07
     SC
    0.06
    .Create
    0.06
    Include
    0.06
    Included
    0.06
    Act Density 0.073%

    No Known Activations