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

    Neuronpedia

    INDEX
    Explanations

    Titles and examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     அதை
    -0.10
     занима
    -0.09
     उसे
    -0.09
    ONENT
    -0.09
     зарегистр
    -0.08
     اسے
    -0.08
     sentença
    -0.08
     specializes
    -0.08
     مسب
    -0.08
     decimal
    -0.08
    POSITIVE LOGITS
    classic
    0.09
     കഥാപാത്ര
    0.09
     clássico
    0.09
     famous
    0.09
     classic
    0.08
     clásico
    0.08
    人物
    0.08
     культ
    0.08
     classiques
    0.08
     famoso
    0.08
    Act Density 0.029%

    No Known Activations