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

    Neuronpedia

    INDEX
    Explanations

    mixed languages and encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     profi
    -0.08
     inuit
    -0.08
     rooftop
    -0.08
     Atr
    -0.07
     படம்
    -0.07
    rscheinlich
    -0.07
    .Cluster
    -0.07
    ugb
    -0.07
     முற
    -0.07
     Cathedral
    -0.07
    POSITIVE LOGITS
     વસ્તુ
    0.10
     benda
    0.10
    事项
    0.09
    -chave
    0.08
     Sold
    0.08
     мебели
    0.08
    .quantity
    0.08
     वस्त
    0.08
    äld
    0.08
     depreci
    0.08
    Act Density 0.051%

    No Known Activations