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

    Neuronpedia

    INDEX
    Explanations

    General English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ોએ
    -0.08
    /com
    -0.08
    /component
    -0.08
     Buckingham
    -0.08
     مرحله
    -0.08
     parfaite
    -0.08
     Armen
    -0.07
     Catarina
    -0.07
     آغاز
    -0.07
     beziehungsweise
    -0.07
    POSITIVE LOGITS
     object
    0.08
     siun
    0.08
    Txn
    0.08
     baby
    0.08
     Trotzdem
    0.08
    .EMAIL
    0.07
     election
    0.07
    ursing
    0.07
    oter
    0.07
     dennoch
    0.07
    Act Density 0.000%

    No Known Activations