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

    Neuronpedia

    INDEX
    Explanations

    We

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     округ
    -0.07
     органов
    -0.07
     тест
    -0.07
     liken
    -0.06
     chatt
    -0.06
     Lost
    -0.06
    sville
    -0.06
     erst
    -0.06
     beiden
    -0.06
     para
    -0.06
    POSITIVE LOGITS
    	I
    0.07
    _pred
    0.06
     helicopters
    0.06
    /documents
    0.06
     Aer
    0.06
    ανδ
    0.06
    тура
    0.06
     DISTINCT
    0.06
    ImageSharp
    0.06
    .struct
    0.06
    Act Density 0.000%

    No Known Activations