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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olacağ
    -0.07
    养
    -0.06
     σχέ
    -0.06
    Spain
    -0.06
    .session
    -0.06
    अ
    -0.06
     zoning
    -0.06
    北京
    -0.06
     Rek
    -0.06
     أغسطس
    -0.06
    POSITIVE LOGITS
     glamorous
    0.07
     anon
    0.06
    .datatables
    0.06
    .guid
    0.06
    iswa
    0.06
    験
    0.06
     violated
    0.06
    گری
    0.06
     PROT
    0.06
     items
    0.06
    Act Density 0.001%

    No Known Activations