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

    Neuronpedia

    INDEX
    Explanations

    similarity in different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     остается
    -0.09
     короб
    -0.09
    历山大发
    -0.09
    astikan
    -0.09
     edilen
    -0.09
     takaisin
    -0.09
     puhul
    -0.08
     akeh
    -0.08
     көптеген
    -0.08
     nuair
    -0.08
    POSITIVE LOGITS
     ähnliche
    0.11
     gespecialiseerd
    0.10
     similar
    0.10
    符合
    0.10
    对此
    0.10
     phù
    0.09
     similares
    0.09
    类似
    0.09
     embody
    0.09
    能够
    0.09
    Act Density 0.051%

    No Known Activations