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

    Neuronpedia

    INDEX
    Explanations

    differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     busca
    -0.08
    раждан
    -0.08
     resides
    -0.08
     வக
    -0.08
     спут
    -0.07
     recinto
    -0.07
    credi
    -0.07
     reside
    -0.07
     competitions
    -0.07
     có
    -0.07
    POSITIVE LOGITS
     Unterschiede
    0.10
     Differences
    0.09
     nuances
    0.09
     adaptar
    0.09
     différences
    0.09
     differing
    0.09
     unterscheiden
    0.09
     differences
    0.08
     diferenças
    0.08
    Dif
    0.08
    Act Density 0.047%

    No Known Activations