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

    Neuronpedia

    INDEX
    Explanations

    specifically for or in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    仅
    0.52
    ，
    0.50
     ،
    0.49
    ،
    0.48
     فقط
    0.47
     только
    0.46
    すべての
    0.43
    ською
    0.43
     მხოლოდ
    0.43
     обов
    0.43
    POSITIVE LOGITS
     aquellos
    0.54
     dzieci
    0.50
     diejenigen
    0.49
     quienes
    0.48
     niños
    0.47
     politiques
    0.47
     những
    0.46
     gençler
    0.46
     coloro
    0.46
     politischen
    0.46
    Act Density 0.262%

    No Known Activations