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

    Neuronpedia

    INDEX
    Explanations

    physics and math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infectious
    -0.07
    	Image
    -0.07
    και
    -0.06
    _udp
    -0.06
     lành
    -0.06
    .keySet
    -0.06
     nextProps
    -0.06
    Seek
    -0.06
     addict
    -0.06
    .Domain
    -0.06
    POSITIVE LOGITS
     emphasized
    0.07
    atsby
    0.07
    /articles
    0.06
    checking
    0.06
     서로
    0.06
     emphasizing
    0.06
     chance
    0.06
     dances
    0.06
    پس
    0.06
    AMPL
    0.06
    Act Density 0.017%

    No Known Activations