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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    озем
    -0.07
     εμπ
    -0.07
     podp
    -0.07
    (Status
    -0.07
     青
    -0.07
     detachment
    -0.06
    .Find
    -0.06
    ")),
    -0.06
     Bib
    -0.06
     पड
    -0.06
    POSITIVE LOGITS
    riting
    0.06
     LOD
    0.06
     sağlar
    0.06
    anged
    0.06
     використовувати
    0.06
     nail
    0.06
     aktual
    0.06
     اروپا
    0.06
    (mac
    0.06
     mega
    0.06
    Act Density 0.009%

    No Known Activations