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

    Neuronpedia

    INDEX
    Explanations

    role of playing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ем
    0.45
    និយ
    0.41
    fromi
    0.39
    eur
    0.38
     wissenschaft
    0.38
     промышленности
    0.38
    쳤
    0.38
    اة
    0.37
     элемент
    0.37
    ޘ
    0.37
    POSITIVE LOGITS
     focal
    0.41
     tanpa
    0.41
     without
    0.40
    )$$
    0.39
     olduğ
    0.39
     Judges
    0.39
     уже
    0.38
     только
    0.37
    লো
    0.36
     a
    0.36
    Act Density 0.000%

    No Known Activations