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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iali
    -0.07
    ướ
    -0.06
    λια
    -0.06
    .rdf
    -0.06
    لل
    -0.06
     объек
    -0.06
    ież
    -0.06
    aud
    -0.06
    енсив
    -0.06
    attered
    -0.06
    POSITIVE LOGITS
    delay
    0.07
     太
    0.06
    duct
    0.06
     Generic
    0.06
     ра
    0.06
    `\
    0.06
    	test
    0.06
     Pak
    0.06
    \Entity
    0.06
    -tested
    0.06
    Act Density 0.001%

    No Known Activations