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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ctx
    -0.07
     obligated
    -0.07
    patrick
    -0.07
     eskort
    -0.07
    Experts
    -0.06
     Driver
    -0.06
     saja
    -0.06
     surface
    -0.06
    Blog
    -0.06
     PSP
    -0.06
    POSITIVE LOGITS
     what
    0.08
     कव
    0.07
     whatever
    0.06
    	when
    0.06
    ANTED
    0.06
    นว
    0.06
     nouvelle
    0.06
    -tech
    0.06
    (suffix
    0.06
     Ludwig
    0.06
    Act Density 0.023%

    No Known Activations