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

    Neuronpedia

    INDEX
    Explanations

    countries and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undeniably
    0.39
     கைப்ப
    0.39
    achtung
    0.38
     und
    0.38
     accounting
    0.38
     elder
    0.37
    ront
    0.37
    numbered
    0.37
    モーション
    0.36
    ankle
    0.36
    POSITIVE LOGITS
     gelangen
    0.40
     Budapest
    0.40
     વચ્
    0.40
    Austria
    0.40
     austri
    0.40
    ಥವಾ
    0.39
     Pologne
    0.39
     فرنسا
    0.39
     Austro
    0.39
     poln
    0.38
    Act Density 0.003%

    No Known Activations